Upload folder using huggingface_hub

README_deleted.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: other
+base_model: /home/bl3615/data/Goedel-Prover-SFT
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: dpo_dpo_lean_0_b0.03_f0_lr5e-6_e2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# dpo_dpo_lean_0_b0.03_f0_lr5e-6_e2
+
+This model is a fine-tuned version of [/home/bl3615/data/Goedel-Prover-SFT](https://huggingface.co//home/bl3615/data/Goedel-Prover-SFT) on the dpo_lean_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5357
+- Rewards/chosen: -4.1002
+- Rewards/rejected: -5.8239
+- Rewards/accuracies: 0.7566
+- Rewards/margins: 1.7237
+- Logps/chosen: -209.7086
+- Logps/rejected: -266.5144
+- Logits/chosen: -13.4579
+- Logits/rejected: -12.9861
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/chosen | Logps/rejected | Logits/chosen | Logits/rejected |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:------------:|:--------------:|:-------------:|:---------------:|
+| 0.5867        | 0.5329 | 500  | 0.5393          | -1.7260        | -2.3840          | 0.7138             | 0.6580          | -130.5684    | -151.8518      | -4.1731       | -3.9948         |
+| 0.1708        | 1.0650 | 1000 | 0.5134          | -4.1008        | -5.5590          | 0.7533             | 1.4582          | -209.7289    | -257.6841      | -11.3604      | -10.9174        |
+| 0.1112        | 1.5979 | 1500 | 0.5428          | -4.2436        | -5.9501          | 0.7599             | 1.7065          | -214.4901    | -270.7217      | -14.0546      | -13.5623        |
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 1.998667732480682,
+    "eval_logits/chosen": -13.45787239074707,
+    "eval_logits/rejected": -12.986124992370605,
+    "eval_logps/chosen": -209.70858764648438,
+    "eval_logps/rejected": -266.514404296875,
+    "eval_loss": 0.535685658454895,
+    "eval_rewards/accuracies": 0.7565789818763733,
+    "eval_rewards/chosen": -4.100185394287109,
+    "eval_rewards/margins": 1.7237099409103394,
+    "eval_rewards/rejected": -5.823895454406738,
+    "eval_runtime": 15.7482,
+    "eval_samples_per_second": 19.304,
+    "eval_steps_per_second": 2.413,
+    "total_flos": 174218888085504.0,
+    "train_loss": 0.33488652056087054,
+    "train_runtime": 7850.5465,
+    "train_samples_per_second": 7.649,
+    "train_steps_per_second": 0.239
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "vocab_size": 102400
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.998667732480682,
+    "eval_logits/chosen": -13.45787239074707,
+    "eval_logits/rejected": -12.986124992370605,
+    "eval_logps/chosen": -209.70858764648438,
+    "eval_logps/rejected": -266.514404296875,
+    "eval_loss": 0.535685658454895,
+    "eval_rewards/accuracies": 0.7565789818763733,
+    "eval_rewards/chosen": -4.100185394287109,
+    "eval_rewards/margins": 1.7237099409103394,
+    "eval_rewards/rejected": -5.823895454406738,
+    "eval_runtime": 15.7482,
+    "eval_samples_per_second": 19.304,
+    "eval_steps_per_second": 2.413
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "transformers_version": "4.48.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e143f3841a70073cdacc0bd99f508f805cae1fc58c382ac4befab9b879cad0d
+size 4987202208

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f2b94af978be50e14c2933fa6a296c052603e6654f377dab7d088cf9c4e72c
+size 4980945440

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146a0af71db8c4fbb39dd1f32cebfd243a9c3bc91ae56544a6248f0de2598ccf
+size 3852615520

model.safetensors.index.json

@@ -0,0 +1,280 @@
+{
+  "metadata": {
+    "total_size": 13820731392
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{%- set found_item = false -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set found_item = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- if not found_item -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{{'### Response:\\n'}}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.998667732480682,
+    "total_flos": 174218888085504.0,
+    "train_loss": 0.33488652056087054,
+    "train_runtime": 7850.5465,
+    "train_samples_per_second": 7.649,
+    "train_steps_per_second": 0.239
+}

trainer_log.jsonl

@@ -0,0 +1,191 @@
+{"current_steps": 10, "total_steps": 1876, "loss": 0.6935, "accuracy": 0.40937501192092896, "lr": 2.6595744680851066e-07, "epoch": 0.010658140154543033, "percentage": 0.53, "elapsed_time": "0:00:44", "remaining_time": "2:19:50"}
+{"current_steps": 20, "total_steps": 1876, "loss": 0.6923, "accuracy": 0.534375011920929, "lr": 5.319148936170213e-07, "epoch": 0.021316280309086066, "percentage": 1.07, "elapsed_time": "0:01:27", "remaining_time": "2:15:49"}
+{"current_steps": 30, "total_steps": 1876, "loss": 0.6933, "accuracy": 0.5062500238418579, "lr": 7.97872340425532e-07, "epoch": 0.0319744204636291, "percentage": 1.6, "elapsed_time": "0:02:09", "remaining_time": "2:12:49"}
+{"current_steps": 40, "total_steps": 1876, "loss": 0.6924, "accuracy": 0.518750011920929, "lr": 1.0638297872340427e-06, "epoch": 0.04263256061817213, "percentage": 2.13, "elapsed_time": "0:02:51", "remaining_time": "2:11:15"}
+{"current_steps": 50, "total_steps": 1876, "loss": 0.6923, "accuracy": 0.5437500476837158, "lr": 1.3297872340425533e-06, "epoch": 0.05329070077271516, "percentage": 2.67, "elapsed_time": "0:03:33", "remaining_time": "2:10:09"}
+{"current_steps": 60, "total_steps": 1876, "loss": 0.6915, "accuracy": 0.503125011920929, "lr": 1.595744680851064e-06, "epoch": 0.0639488409272582, "percentage": 3.2, "elapsed_time": "0:04:16", "remaining_time": "2:09:15"}
+{"current_steps": 70, "total_steps": 1876, "loss": 0.6897, "accuracy": 0.612500011920929, "lr": 1.8617021276595745e-06, "epoch": 0.07460698108180122, "percentage": 3.73, "elapsed_time": "0:05:00", "remaining_time": "2:09:12"}
+{"current_steps": 80, "total_steps": 1876, "loss": 0.6876, "accuracy": 0.609375, "lr": 2.1276595744680853e-06, "epoch": 0.08526512123634426, "percentage": 4.26, "elapsed_time": "0:05:41", "remaining_time": "2:07:38"}
+{"current_steps": 90, "total_steps": 1876, "loss": 0.6848, "accuracy": 0.621874988079071, "lr": 2.393617021276596e-06, "epoch": 0.09592326139088729, "percentage": 4.8, "elapsed_time": "0:06:20", "remaining_time": "2:05:57"}
+{"current_steps": 100, "total_steps": 1876, "loss": 0.68, "accuracy": 0.628125011920929, "lr": 2.6595744680851065e-06, "epoch": 0.10658140154543032, "percentage": 5.33, "elapsed_time": "0:07:03", "remaining_time": "2:05:29"}
+{"current_steps": 110, "total_steps": 1876, "loss": 0.6765, "accuracy": 0.6218750476837158, "lr": 2.9255319148936174e-06, "epoch": 0.11723954169997336, "percentage": 5.86, "elapsed_time": "0:07:44", "remaining_time": "2:04:18"}
+{"current_steps": 120, "total_steps": 1876, "loss": 0.6677, "accuracy": 0.640625, "lr": 3.191489361702128e-06, "epoch": 0.1278976818545164, "percentage": 6.4, "elapsed_time": "0:08:26", "remaining_time": "2:03:25"}
+{"current_steps": 130, "total_steps": 1876, "loss": 0.6542, "accuracy": 0.668749988079071, "lr": 3.457446808510639e-06, "epoch": 0.13855582200905942, "percentage": 6.93, "elapsed_time": "0:09:05", "remaining_time": "2:02:08"}
+{"current_steps": 140, "total_steps": 1876, "loss": 0.6594, "accuracy": 0.6406250596046448, "lr": 3.723404255319149e-06, "epoch": 0.14921396216360244, "percentage": 7.46, "elapsed_time": "0:09:46", "remaining_time": "2:01:18"}
+{"current_steps": 150, "total_steps": 1876, "loss": 0.6289, "accuracy": 0.671875, "lr": 3.98936170212766e-06, "epoch": 0.15987210231814547, "percentage": 8.0, "elapsed_time": "0:10:29", "remaining_time": "2:00:43"}
+{"current_steps": 160, "total_steps": 1876, "loss": 0.6201, "accuracy": 0.643750011920929, "lr": 4.255319148936171e-06, "epoch": 0.17053024247268853, "percentage": 8.53, "elapsed_time": "0:11:09", "remaining_time": "1:59:42"}
+{"current_steps": 170, "total_steps": 1876, "loss": 0.6527, "accuracy": 0.6000000238418579, "lr": 4.521276595744681e-06, "epoch": 0.18118838262723155, "percentage": 9.06, "elapsed_time": "0:11:52", "remaining_time": "1:59:06"}
+{"current_steps": 180, "total_steps": 1876, "loss": 0.6232, "accuracy": 0.6531250476837158, "lr": 4.787234042553192e-06, "epoch": 0.19184652278177458, "percentage": 9.59, "elapsed_time": "0:12:35", "remaining_time": "1:58:38"}
+{"current_steps": 190, "total_steps": 1876, "loss": 0.6573, "accuracy": 0.590624988079071, "lr": 4.999982680938129e-06, "epoch": 0.2025046629363176, "percentage": 10.13, "elapsed_time": "0:13:18", "remaining_time": "1:58:01"}
+{"current_steps": 200, "total_steps": 1876, "loss": 0.6258, "accuracy": 0.643750011920929, "lr": 4.999376538968061e-06, "epoch": 0.21316280309086064, "percentage": 10.66, "elapsed_time": "0:14:02", "remaining_time": "1:57:40"}
+{"current_steps": 210, "total_steps": 1876, "loss": 0.622, "accuracy": 0.628125011920929, "lr": 4.997904683849418e-06, "epoch": 0.22382094324540366, "percentage": 11.19, "elapsed_time": "0:14:42", "remaining_time": "1:56:42"}
+{"current_steps": 220, "total_steps": 1876, "loss": 0.6036, "accuracy": 0.6656249761581421, "lr": 4.9955676253910716e-06, "epoch": 0.23447908339994672, "percentage": 11.73, "elapsed_time": "0:15:26", "remaining_time": "1:56:16"}
+{"current_steps": 230, "total_steps": 1876, "loss": 0.6068, "accuracy": 0.675000011920929, "lr": 4.992366173083788e-06, "epoch": 0.24513722355448975, "percentage": 12.26, "elapsed_time": "0:16:10", "remaining_time": "1:55:44"}
+{"current_steps": 240, "total_steps": 1876, "loss": 0.6553, "accuracy": 0.6031249761581421, "lr": 4.988301435819853e-06, "epoch": 0.2557953637090328, "percentage": 12.79, "elapsed_time": "0:16:53", "remaining_time": "1:55:11"}
+{"current_steps": 250, "total_steps": 1876, "loss": 0.623, "accuracy": 0.684374988079071, "lr": 4.983374821508974e-06, "epoch": 0.2664535038635758, "percentage": 13.33, "elapsed_time": "0:17:36", "remaining_time": "1:54:29"}
+{"current_steps": 260, "total_steps": 1876, "loss": 0.5669, "accuracy": 0.7156250476837158, "lr": 4.977588036590625e-06, "epoch": 0.27711164401811883, "percentage": 13.86, "elapsed_time": "0:18:18", "remaining_time": "1:53:45"}
+{"current_steps": 270, "total_steps": 1876, "loss": 0.6231, "accuracy": 0.668749988079071, "lr": 4.970943085442984e-06, "epoch": 0.28776978417266186, "percentage": 14.39, "elapsed_time": "0:18:59", "remaining_time": "1:52:59"}
+{"current_steps": 280, "total_steps": 1876, "loss": 0.6445, "accuracy": 0.637499988079071, "lr": 4.963442269688671e-06, "epoch": 0.2984279243272049, "percentage": 14.93, "elapsed_time": "0:19:41", "remaining_time": "1:52:16"}
+{"current_steps": 290, "total_steps": 1876, "loss": 0.5879, "accuracy": 0.703125, "lr": 4.955088187397535e-06, "epoch": 0.3090860644817479, "percentage": 15.46, "elapsed_time": "0:20:23", "remaining_time": "1:51:33"}
+{"current_steps": 300, "total_steps": 1876, "loss": 0.5798, "accuracy": 0.7093750238418579, "lr": 4.9458837321867515e-06, "epoch": 0.31974420463629094, "percentage": 15.99, "elapsed_time": "0:21:05", "remaining_time": "1:50:49"}
+{"current_steps": 310, "total_steps": 1876, "loss": 0.5732, "accuracy": 0.684374988079071, "lr": 4.935832092218559e-06, "epoch": 0.330402344790834, "percentage": 16.52, "elapsed_time": "0:21:45", "remaining_time": "1:49:55"}
+{"current_steps": 320, "total_steps": 1876, "loss": 0.5751, "accuracy": 0.699999988079071, "lr": 4.92493674909597e-06, "epoch": 0.34106048494537705, "percentage": 17.06, "elapsed_time": "0:22:28", "remaining_time": "1:49:16"}
+{"current_steps": 330, "total_steps": 1876, "loss": 0.5474, "accuracy": 0.7124999761581421, "lr": 4.913201476656839e-06, "epoch": 0.3517186250999201, "percentage": 17.59, "elapsed_time": "0:23:09", "remaining_time": "1:48:30"}
+{"current_steps": 340, "total_steps": 1876, "loss": 0.5318, "accuracy": 0.7093750238418579, "lr": 4.900630339666718e-06, "epoch": 0.3623767652544631, "percentage": 18.12, "elapsed_time": "0:23:50", "remaining_time": "1:47:42"}
+{"current_steps": 350, "total_steps": 1876, "loss": 0.6146, "accuracy": 0.668749988079071, "lr": 4.887227692410931e-06, "epoch": 0.37303490540900613, "percentage": 18.66, "elapsed_time": "0:24:33", "remaining_time": "1:47:03"}
+{"current_steps": 360, "total_steps": 1876, "loss": 0.5883, "accuracy": 0.7156250476837158, "lr": 4.8729981771863754e-06, "epoch": 0.38369304556354916, "percentage": 19.19, "elapsed_time": "0:25:13", "remaining_time": "1:46:11"}
+{"current_steps": 370, "total_steps": 1876, "loss": 0.5682, "accuracy": 0.7000000476837158, "lr": 4.857946722693566e-06, "epoch": 0.3943511857180922, "percentage": 19.72, "elapsed_time": "0:25:52", "remaining_time": "1:45:20"}
+{"current_steps": 380, "total_steps": 1876, "loss": 0.5421, "accuracy": 0.7281249761581421, "lr": 4.8420785423294645e-06, "epoch": 0.4050093258726352, "percentage": 20.26, "elapsed_time": "0:26:33", "remaining_time": "1:44:35"}
+{"current_steps": 390, "total_steps": 1876, "loss": 0.5662, "accuracy": 0.715624988079071, "lr": 4.825399132381714e-06, "epoch": 0.41566746602717825, "percentage": 20.79, "elapsed_time": "0:27:14", "remaining_time": "1:43:48"}
+{"current_steps": 400, "total_steps": 1876, "loss": 0.5967, "accuracy": 0.6937500238418579, "lr": 4.807914270124877e-06, "epoch": 0.4263256061817213, "percentage": 21.32, "elapsed_time": "0:27:56", "remaining_time": "1:43:07"}
+{"current_steps": 410, "total_steps": 1876, "loss": 0.562, "accuracy": 0.6875, "lr": 4.789630011819355e-06, "epoch": 0.4369837463362643, "percentage": 21.86, "elapsed_time": "0:28:39", "remaining_time": "1:42:27"}
+{"current_steps": 420, "total_steps": 1876, "loss": 0.5591, "accuracy": 0.7062500715255737, "lr": 4.770552690613665e-06, "epoch": 0.44764188649080733, "percentage": 22.39, "elapsed_time": "0:29:20", "remaining_time": "1:41:41"}
+{"current_steps": 430, "total_steps": 1876, "loss": 0.5378, "accuracy": 0.7031250596046448, "lr": 4.750688914350825e-06, "epoch": 0.4583000266453504, "percentage": 22.92, "elapsed_time": "0:30:02", "remaining_time": "1:41:01"}
+{"current_steps": 440, "total_steps": 1876, "loss": 0.5869, "accuracy": 0.6781250238418579, "lr": 4.7300455632795774e-06, "epoch": 0.46895816679989344, "percentage": 23.45, "elapsed_time": "0:30:43", "remaining_time": "1:40:15"}
+{"current_steps": 450, "total_steps": 1876, "loss": 0.5314, "accuracy": 0.7124999761581421, "lr": 4.708629787671268e-06, "epoch": 0.47961630695443647, "percentage": 23.99, "elapsed_time": "0:31:24", "remaining_time": "1:39:31"}
+{"current_steps": 460, "total_steps": 1876, "loss": 0.5613, "accuracy": 0.71875, "lr": 4.6864490053432e-06, "epoch": 0.4902744471089795, "percentage": 24.52, "elapsed_time": "0:32:05", "remaining_time": "1:38:48"}
+{"current_steps": 470, "total_steps": 1876, "loss": 0.5057, "accuracy": 0.731249988079071, "lr": 4.663510899089304e-06, "epoch": 0.5009325872635225, "percentage": 25.05, "elapsed_time": "0:32:44", "remaining_time": "1:37:56"}
+{"current_steps": 480, "total_steps": 1876, "loss": 0.5665, "accuracy": 0.6968749761581421, "lr": 4.639823414019042e-06, "epoch": 0.5115907274180655, "percentage": 25.59, "elapsed_time": "0:33:25", "remaining_time": "1:37:12"}
+{"current_steps": 490, "total_steps": 1876, "loss": 0.5575, "accuracy": 0.6875, "lr": 4.615394754805444e-06, "epoch": 0.5222488675726086, "percentage": 26.12, "elapsed_time": "0:34:07", "remaining_time": "1:36:30"}
+{"current_steps": 500, "total_steps": 1876, "loss": 0.5867, "accuracy": 0.690625011920929, "lr": 4.590233382843242e-06, "epoch": 0.5329070077271516, "percentage": 26.65, "elapsed_time": "0:34:47", "remaining_time": "1:35:43"}
+{"current_steps": 500, "total_steps": 1876, "eval_loss": 0.5392829775810242, "epoch": 0.5329070077271516, "percentage": 26.65, "elapsed_time": "0:35:03", "remaining_time": "1:36:28"}
+{"current_steps": 510, "total_steps": 1876, "loss": 0.54, "accuracy": 0.737500011920929, "lr": 4.564348013318086e-06, "epoch": 0.5435651478816946, "percentage": 27.19, "elapsed_time": "0:35:43", "remaining_time": "1:35:41"}
+{"current_steps": 520, "total_steps": 1876, "loss": 0.5293, "accuracy": 0.7156250476837158, "lr": 4.537747612187848e-06, "epoch": 0.5542232880362377, "percentage": 27.72, "elapsed_time": "0:36:23", "remaining_time": "1:34:54"}
+{"current_steps": 530, "total_steps": 1876, "loss": 0.5617, "accuracy": 0.7000000476837158, "lr": 4.51044139307707e-06, "epoch": 0.5648814281907807, "percentage": 28.25, "elapsed_time": "0:37:04", "remaining_time": "1:34:08"}
+{"current_steps": 540, "total_steps": 1876, "loss": 0.4848, "accuracy": 0.7625000476837158, "lr": 4.48243881408562e-06, "epoch": 0.5755395683453237, "percentage": 28.78, "elapsed_time": "0:37:46", "remaining_time": "1:33:27"}
+{"current_steps": 550, "total_steps": 1876, "loss": 0.5297, "accuracy": 0.7593750357627869, "lr": 4.453749574512686e-06, "epoch": 0.5861977084998667, "percentage": 29.32, "elapsed_time": "0:38:29", "remaining_time": "1:32:47"}
+{"current_steps": 560, "total_steps": 1876, "loss": 0.494, "accuracy": 0.7687500715255737, "lr": 4.424383611497201e-06, "epoch": 0.5968558486544098, "percentage": 29.85, "elapsed_time": "0:39:10", "remaining_time": "1:32:04"}
+{"current_steps": 570, "total_steps": 1876, "loss": 0.5092, "accuracy": 0.7281250357627869, "lr": 4.3943510965759115e-06, "epoch": 0.6075139888089528, "percentage": 30.38, "elapsed_time": "0:39:53", "remaining_time": "1:31:25"}
+{"current_steps": 580, "total_steps": 1876, "loss": 0.5473, "accuracy": 0.7249999642372131, "lr": 4.363662432160236e-06, "epoch": 0.6181721289634958, "percentage": 30.92, "elapsed_time": "0:40:35", "remaining_time": "1:30:42"}
+{"current_steps": 590, "total_steps": 1876, "loss": 0.5137, "accuracy": 0.721875011920929, "lr": 4.332328247933172e-06, "epoch": 0.6288302691180389, "percentage": 31.45, "elapsed_time": "0:41:15", "remaining_time": "1:29:55"}
+{"current_steps": 600, "total_steps": 1876, "loss": 0.4583, "accuracy": 0.7562499642372131, "lr": 4.30035939716747e-06, "epoch": 0.6394884092725819, "percentage": 31.98, "elapsed_time": "0:41:55", "remaining_time": "1:29:09"}
+{"current_steps": 610, "total_steps": 1876, "loss": 0.5508, "accuracy": 0.734375, "lr": 4.267766952966369e-06, "epoch": 0.650146549427125, "percentage": 32.52, "elapsed_time": "0:42:37", "remaining_time": "1:28:26"}
+{"current_steps": 620, "total_steps": 1876, "loss": 0.4985, "accuracy": 0.778124988079071, "lr": 4.234562204428192e-06, "epoch": 0.660804689581668, "percentage": 33.05, "elapsed_time": "0:43:20", "remaining_time": "1:27:47"}
+{"current_steps": 630, "total_steps": 1876, "loss": 0.5229, "accuracy": 0.706250011920929, "lr": 4.200756652736115e-06, "epoch": 0.6714628297362111, "percentage": 33.58, "elapsed_time": "0:44:00", "remaining_time": "1:27:01"}
+{"current_steps": 640, "total_steps": 1876, "loss": 0.5288, "accuracy": 0.715624988079071, "lr": 4.16636200717449e-06, "epoch": 0.6821209698907541, "percentage": 34.12, "elapsed_time": "0:44:40", "remaining_time": "1:26:17"}
+{"current_steps": 650, "total_steps": 1876, "loss": 0.5322, "accuracy": 0.753125011920929, "lr": 4.131390181073076e-06, "epoch": 0.6927791100452971, "percentage": 34.65, "elapsed_time": "0:45:22", "remaining_time": "1:25:35"}
+{"current_steps": 660, "total_steps": 1876, "loss": 0.5081, "accuracy": 0.7500000596046448, "lr": 4.095853287680604e-06, "epoch": 0.7034372501998402, "percentage": 35.18, "elapsed_time": "0:46:04", "remaining_time": "1:24:53"}
+{"current_steps": 670, "total_steps": 1876, "loss": 0.498, "accuracy": 0.7312500476837158, "lr": 4.059763635969086e-06, "epoch": 0.7140953903543832, "percentage": 35.71, "elapsed_time": "0:46:46", "remaining_time": "1:24:11"}
+{"current_steps": 680, "total_steps": 1876, "loss": 0.4888, "accuracy": 0.7500000596046448, "lr": 4.023133726370342e-06, "epoch": 0.7247535305089262, "percentage": 36.25, "elapsed_time": "0:47:26", "remaining_time": "1:23:27"}
+{"current_steps": 690, "total_steps": 1876, "loss": 0.483, "accuracy": 0.7656250596046448, "lr": 3.985976246446199e-06, "epoch": 0.7354116706634692, "percentage": 36.78, "elapsed_time": "0:48:11", "remaining_time": "1:22:50"}
+{"current_steps": 700, "total_steps": 1876, "loss": 0.5577, "accuracy": 0.731249988079071, "lr": 3.948304066493885e-06, "epoch": 0.7460698108180123, "percentage": 37.31, "elapsed_time": "0:48:53", "remaining_time": "1:22:07"}
+{"current_steps": 710, "total_steps": 1876, "loss": 0.5002, "accuracy": 0.762499988079071, "lr": 3.910130235088119e-06, "epoch": 0.7567279509725553, "percentage": 37.85, "elapsed_time": "0:49:33", "remaining_time": "1:21:23"}
+{"current_steps": 720, "total_steps": 1876, "loss": 0.4679, "accuracy": 0.765625, "lr": 3.871467974561456e-06, "epoch": 0.7673860911270983, "percentage": 38.38, "elapsed_time": "0:50:14", "remaining_time": "1:20:39"}
+{"current_steps": 730, "total_steps": 1876, "loss": 0.5222, "accuracy": 0.731249988079071, "lr": 3.832330676424445e-06, "epoch": 0.7780442312816414, "percentage": 38.91, "elapsed_time": "0:50:54", "remaining_time": "1:19:55"}
+{"current_steps": 740, "total_steps": 1876, "loss": 0.5222, "accuracy": 0.715624988079071, "lr": 3.7927318967271966e-06, "epoch": 0.7887023714361844, "percentage": 39.45, "elapsed_time": "0:51:36", "remaining_time": "1:19:13"}
+{"current_steps": 750, "total_steps": 1876, "loss": 0.5075, "accuracy": 0.75, "lr": 3.752685351363938e-06, "epoch": 0.7993605115907274, "percentage": 39.98, "elapsed_time": "0:52:17", "remaining_time": "1:18:31"}
+{"current_steps": 760, "total_steps": 1876, "loss": 0.5072, "accuracy": 0.765625, "lr": 3.7122049113222286e-06, "epoch": 0.8100186517452704, "percentage": 40.51, "elapsed_time": "0:52:59", "remaining_time": "1:17:48"}
+{"current_steps": 770, "total_steps": 1876, "loss": 0.5012, "accuracy": 0.7562500238418579, "lr": 3.671304597878438e-06, "epoch": 0.8206767918998135, "percentage": 41.04, "elapsed_time": "0:53:42", "remaining_time": "1:17:08"}
+{"current_steps": 780, "total_steps": 1876, "loss": 0.5271, "accuracy": 0.746874988079071, "lr": 3.6299985777411744e-06, "epoch": 0.8313349320543565, "percentage": 41.58, "elapsed_time": "0:54:26", "remaining_time": "1:16:29"}
+{"current_steps": 790, "total_steps": 1876, "loss": 0.5205, "accuracy": 0.753125011920929, "lr": 3.5883011581443384e-06, "epoch": 0.8419930722088995, "percentage": 42.11, "elapsed_time": "0:55:08", "remaining_time": "1:15:48"}
+{"current_steps": 800, "total_steps": 1876, "loss": 0.4845, "accuracy": 0.7781250476837158, "lr": 3.5462267818915014e-06, "epoch": 0.8526512123634425, "percentage": 42.64, "elapsed_time": "0:55:51", "remaining_time": "1:15:07"}
+{"current_steps": 810, "total_steps": 1876, "loss": 0.4796, "accuracy": 0.7593750357627869, "lr": 3.503790022353333e-06, "epoch": 0.8633093525179856, "percentage": 43.18, "elapsed_time": "0:56:34", "remaining_time": "1:14:26"}
+{"current_steps": 820, "total_steps": 1876, "loss": 0.4763, "accuracy": 0.7875000238418579, "lr": 3.4610055784197917e-06, "epoch": 0.8739674926725286, "percentage": 43.71, "elapsed_time": "0:57:14", "remaining_time": "1:13:42"}
+{"current_steps": 830, "total_steps": 1876, "loss": 0.5057, "accuracy": 0.7312500476837158, "lr": 3.417888269408851e-06, "epoch": 0.8846256328270716, "percentage": 44.24, "elapsed_time": "0:57:53", "remaining_time": "1:12:57"}
+{"current_steps": 840, "total_steps": 1876, "loss": 0.4856, "accuracy": 0.7468750476837158, "lr": 3.3744530299335093e-06, "epoch": 0.8952837729816147, "percentage": 44.78, "elapsed_time": "0:58:36", "remaining_time": "1:12:16"}
+{"current_steps": 850, "total_steps": 1876, "loss": 0.4603, "accuracy": 0.793749988079071, "lr": 3.330714904728858e-06, "epoch": 0.9059419131361578, "percentage": 45.31, "elapsed_time": "0:59:17", "remaining_time": "1:11:33"}
+{"current_steps": 860, "total_steps": 1876, "loss": 0.5225, "accuracy": 0.734375, "lr": 3.2866890434410153e-06, "epoch": 0.9166000532907008, "percentage": 45.84, "elapsed_time": "0:59:57", "remaining_time": "1:10:50"}
+{"current_steps": 870, "total_steps": 1876, "loss": 0.5126, "accuracy": 0.753125011920929, "lr": 3.2423906953797214e-06, "epoch": 0.9272581934452439, "percentage": 46.38, "elapsed_time": "1:00:40", "remaining_time": "1:10:10"}
+{"current_steps": 880, "total_steps": 1876, "loss": 0.4621, "accuracy": 0.7718750238418579, "lr": 3.1978352042364026e-06, "epoch": 0.9379163335997869, "percentage": 46.91, "elapsed_time": "1:01:21", "remaining_time": "1:09:26"}
+{"current_steps": 890, "total_steps": 1876, "loss": 0.5007, "accuracy": 0.7593749761581421, "lr": 3.1530380027695584e-06, "epoch": 0.9485744737543299, "percentage": 47.44, "elapsed_time": "1:02:02", "remaining_time": "1:08:43"}
+{"current_steps": 900, "total_steps": 1876, "loss": 0.4835, "accuracy": 0.762499988079071, "lr": 3.1080146074592882e-06, "epoch": 0.9592326139088729, "percentage": 47.97, "elapsed_time": "1:02:43", "remaining_time": "1:08:00"}
+{"current_steps": 910, "total_steps": 1876, "loss": 0.529, "accuracy": 0.721875011920929, "lr": 3.0627806131328254e-06, "epoch": 0.969890754063416, "percentage": 48.51, "elapsed_time": "1:03:22", "remaining_time": "1:07:16"}
+{"current_steps": 920, "total_steps": 1876, "loss": 0.4982, "accuracy": 0.765625, "lr": 3.0173516875629282e-06, "epoch": 0.980548894217959, "percentage": 49.04, "elapsed_time": "1:04:03", "remaining_time": "1:06:33"}
+{"current_steps": 930, "total_steps": 1876, "loss": 0.4984, "accuracy": 0.746874988079071, "lr": 2.9717435660410092e-06, "epoch": 0.991207034372502, "percentage": 49.57, "elapsed_time": "1:04:46", "remaining_time": "1:05:52"}
+{"current_steps": 940, "total_steps": 1876, "loss": 0.4402, "accuracy": 0.7736486196517944, "lr": 2.9259720459268782e-06, "epoch": 1.0010658140154542, "percentage": 50.11, "elapsed_time": "1:05:27", "remaining_time": "1:05:10"}
+{"current_steps": 950, "total_steps": 1876, "loss": 0.157, "accuracy": 0.9781249761581421, "lr": 2.8800529811769797e-06, "epoch": 1.0117239541699974, "percentage": 50.64, "elapsed_time": "1:06:08", "remaining_time": "1:04:28"}
+{"current_steps": 960, "total_steps": 1876, "loss": 0.1387, "accuracy": 0.9750000238418579, "lr": 2.8340022768530406e-06, "epoch": 1.0223820943245403, "percentage": 51.17, "elapsed_time": "1:06:51", "remaining_time": "1:03:47"}
+{"current_steps": 970, "total_steps": 1876, "loss": 0.1503, "accuracy": 0.96875, "lr": 2.7878358836129986e-06, "epoch": 1.0330402344790834, "percentage": 51.71, "elapsed_time": "1:07:33", "remaining_time": "1:03:06"}
+{"current_steps": 980, "total_steps": 1876, "loss": 0.1402, "accuracy": 0.956250011920929, "lr": 2.7415697921861527e-06, "epoch": 1.0436983746336264, "percentage": 52.24, "elapsed_time": "1:08:15", "remaining_time": "1:02:24"}
+{"current_steps": 990, "total_steps": 1876, "loss": 0.1348, "accuracy": 0.9625000357627869, "lr": 2.695220027834426e-06, "epoch": 1.0543565147881695, "percentage": 52.77, "elapsed_time": "1:08:58", "remaining_time": "1:01:43"}
+{"current_steps": 1000, "total_steps": 1876, "loss": 0.1708, "accuracy": 0.9437500238418579, "lr": 2.648802644801669e-06, "epoch": 1.0650146549427124, "percentage": 53.3, "elapsed_time": "1:09:39", "remaining_time": "1:01:01"}
+{"current_steps": 1000, "total_steps": 1876, "eval_loss": 0.5134132504463196, "epoch": 1.0650146549427124, "percentage": 53.3, "elapsed_time": "1:09:55", "remaining_time": "1:01:15"}
+{"current_steps": 1010, "total_steps": 1876, "loss": 0.1212, "accuracy": 0.9593750238418579, "lr": 2.6023337207529276e-06, "epoch": 1.0756727950972556, "percentage": 53.84, "elapsed_time": "1:10:40", "remaining_time": "1:00:35"}
+{"current_steps": 1020, "total_steps": 1876, "loss": 0.0932, "accuracy": 0.9750000238418579, "lr": 2.5558293512055927e-06, "epoch": 1.0863309352517985, "percentage": 54.37, "elapsed_time": "1:11:23", "remaining_time": "0:59:54"}
+{"current_steps": 1030, "total_steps": 1876, "loss": 0.1374, "accuracy": 0.9593750238418579, "lr": 2.509305643954369e-06, "epoch": 1.0969890754063416, "percentage": 54.9, "elapsed_time": "1:12:04", "remaining_time": "0:59:11"}
+{"current_steps": 1040, "total_steps": 1876, "loss": 0.1105, "accuracy": 0.9718749523162842, "lr": 2.462778713491995e-06, "epoch": 1.1076472155608845, "percentage": 55.44, "elapsed_time": "1:12:42", "remaining_time": "0:58:26"}
+{"current_steps": 1050, "total_steps": 1876, "loss": 0.1004, "accuracy": 0.9687500596046448, "lr": 2.41626467542764e-06, "epoch": 1.1183053557154277, "percentage": 55.97, "elapsed_time": "1:13:24", "remaining_time": "0:57:44"}
+{"current_steps": 1060, "total_steps": 1876, "loss": 0.1212, "accuracy": 0.956250011920929, "lr": 2.3697796409049094e-06, "epoch": 1.1289634958699706, "percentage": 56.5, "elapsed_time": "1:14:05", "remaining_time": "0:57:01"}
+{"current_steps": 1070, "total_steps": 1876, "loss": 0.1031, "accuracy": 0.96875, "lr": 2.323339711021405e-06, "epoch": 1.1396216360245137, "percentage": 57.04, "elapsed_time": "1:14:47", "remaining_time": "0:56:20"}
+{"current_steps": 1080, "total_steps": 1876, "loss": 0.0929, "accuracy": 0.9812500476837158, "lr": 2.2769609712517606e-06, "epoch": 1.1502797761790569, "percentage": 57.57, "elapsed_time": "1:15:31", "remaining_time": "0:55:39"}
+{"current_steps": 1090, "total_steps": 1876, "loss": 0.1015, "accuracy": 0.9625000357627869, "lr": 2.2306594858760904e-06, "epoch": 1.1609379163335998, "percentage": 58.1, "elapsed_time": "1:16:12", "remaining_time": "0:54:56"}
+{"current_steps": 1100, "total_steps": 1876, "loss": 0.1184, "accuracy": 0.9656250476837158, "lr": 2.1844512924157783e-06, "epoch": 1.171596056488143, "percentage": 58.64, "elapsed_time": "1:16:52", "remaining_time": "0:54:13"}
+{"current_steps": 1110, "total_steps": 1876, "loss": 0.1063, "accuracy": 0.96875, "lr": 2.1383523960785346e-06, "epoch": 1.1822541966426858, "percentage": 59.17, "elapsed_time": "1:17:32", "remaining_time": "0:53:30"}
+{"current_steps": 1120, "total_steps": 1876, "loss": 0.1211, "accuracy": 0.9500000476837158, "lr": 2.0923787642146438e-06, "epoch": 1.192912336797229, "percentage": 59.7, "elapsed_time": "1:18:12", "remaining_time": "0:52:47"}
+{"current_steps": 1130, "total_steps": 1876, "loss": 0.0996, "accuracy": 0.96875, "lr": 2.0465463207863313e-06, "epoch": 1.2035704769517719, "percentage": 60.23, "elapsed_time": "1:18:51", "remaining_time": "0:52:03"}
+{"current_steps": 1140, "total_steps": 1876, "loss": 0.1323, "accuracy": 0.9468750357627869, "lr": 2.000870940852151e-06, "epoch": 1.214228617106315, "percentage": 60.77, "elapsed_time": "1:19:32", "remaining_time": "0:51:20"}
+{"current_steps": 1150, "total_steps": 1876, "loss": 0.105, "accuracy": 0.96875, "lr": 1.9553684450683197e-06, "epoch": 1.224886757260858, "percentage": 61.3, "elapsed_time": "1:20:11", "remaining_time": "0:50:37"}
+{"current_steps": 1160, "total_steps": 1876, "loss": 0.1175, "accuracy": 0.9656250476837158, "lr": 1.910054594208885e-06, "epoch": 1.235544897415401, "percentage": 61.83, "elapsed_time": "1:20:53", "remaining_time": "0:49:55"}
+{"current_steps": 1170, "total_steps": 1876, "loss": 0.0935, "accuracy": 0.9750000238418579, "lr": 1.8649450837066445e-06, "epoch": 1.246203037569944, "percentage": 62.37, "elapsed_time": "1:21:36", "remaining_time": "0:49:14"}
+{"current_steps": 1180, "total_steps": 1876, "loss": 0.11, "accuracy": 0.953125, "lr": 1.8200555382166901e-06, "epoch": 1.2568611777244871, "percentage": 62.9, "elapsed_time": "1:22:18", "remaining_time": "0:48:32"}
+{"current_steps": 1190, "total_steps": 1876, "loss": 0.1028, "accuracy": 0.9656250476837158, "lr": 1.7754015062044722e-06, "epoch": 1.26751931787903, "percentage": 63.43, "elapsed_time": "1:22:59", "remaining_time": "0:47:50"}
+{"current_steps": 1200, "total_steps": 1876, "loss": 0.0953, "accuracy": 0.971875011920929, "lr": 1.7309984545602531e-06, "epoch": 1.2781774580335732, "percentage": 63.97, "elapsed_time": "1:23:40", "remaining_time": "0:47:08"}
+{"current_steps": 1210, "total_steps": 1876, "loss": 0.1227, "accuracy": 0.9625000357627869, "lr": 1.6868617632418116e-06, "epoch": 1.288835598188116, "percentage": 64.5, "elapsed_time": "1:24:20", "remaining_time": "0:46:25"}
+{"current_steps": 1220, "total_steps": 1876, "loss": 0.0673, "accuracy": 0.9812500476837158, "lr": 1.643006719947266e-06, "epoch": 1.2994937383426592, "percentage": 65.03, "elapsed_time": "1:25:03", "remaining_time": "0:45:44"}
+{"current_steps": 1230, "total_steps": 1876, "loss": 0.0954, "accuracy": 0.971875011920929, "lr": 1.5994485148198441e-06, "epoch": 1.3101518784972022, "percentage": 65.57, "elapsed_time": "1:25:43", "remaining_time": "0:45:01"}
+{"current_steps": 1240, "total_steps": 1876, "loss": 0.091, "accuracy": 0.9781249761581421, "lr": 1.5562022351864535e-06, "epoch": 1.3208100186517453, "percentage": 66.1, "elapsed_time": "1:26:23", "remaining_time": "0:44:18"}
+{"current_steps": 1250, "total_steps": 1876, "loss": 0.087, "accuracy": 0.96875, "lr": 1.5132828603318578e-06, "epoch": 1.3314681588062882, "percentage": 66.63, "elapsed_time": "1:27:03", "remaining_time": "0:43:35"}
+{"current_steps": 1260, "total_steps": 1876, "loss": 0.1034, "accuracy": 0.96875, "lr": 1.470705256310275e-06, "epoch": 1.3421262989608314, "percentage": 67.16, "elapsed_time": "1:27:43", "remaining_time": "0:42:53"}
+{"current_steps": 1270, "total_steps": 1876, "loss": 0.1028, "accuracy": 0.9656250476837158, "lr": 1.4284841707961988e-06, "epoch": 1.3527844391153745, "percentage": 67.7, "elapsed_time": "1:28:28", "remaining_time": "0:42:13"}
+{"current_steps": 1280, "total_steps": 1876, "loss": 0.1074, "accuracy": 0.96875, "lr": 1.386634227976224e-06, "epoch": 1.3634425792699174, "percentage": 68.23, "elapsed_time": "1:29:11", "remaining_time": "0:41:31"}
+{"current_steps": 1290, "total_steps": 1876, "loss": 0.1252, "accuracy": 0.9500000476837158, "lr": 1.3451699234836422e-06, "epoch": 1.3741007194244603, "percentage": 68.76, "elapsed_time": "1:29:54", "remaining_time": "0:40:50"}
+{"current_steps": 1300, "total_steps": 1876, "loss": 0.069, "accuracy": 0.9874999523162842, "lr": 1.3041056193775667e-06, "epoch": 1.3847588595790035, "percentage": 69.3, "elapsed_time": "1:30:36", "remaining_time": "0:40:08"}
+{"current_steps": 1310, "total_steps": 1876, "loss": 0.1738, "accuracy": 0.940625011920929, "lr": 1.263455539168319e-06, "epoch": 1.3954169997335466, "percentage": 69.83, "elapsed_time": "1:31:18", "remaining_time": "0:39:26"}
+{"current_steps": 1320, "total_steps": 1876, "loss": 0.103, "accuracy": 0.965624988079071, "lr": 1.2232337628908106e-06, "epoch": 1.4060751398880895, "percentage": 70.36, "elapsed_time": "1:31:59", "remaining_time": "0:38:44"}
+{"current_steps": 1330, "total_steps": 1876, "loss": 0.1194, "accuracy": 0.9625000357627869, "lr": 1.1834542222276208e-06, "epoch": 1.4167332800426324, "percentage": 70.9, "elapsed_time": "1:32:40", "remaining_time": "0:38:02"}
+{"current_steps": 1340, "total_steps": 1876, "loss": 0.1005, "accuracy": 0.9687500596046448, "lr": 1.1441306956834506e-06, "epoch": 1.4273914201971756, "percentage": 71.43, "elapsed_time": "1:33:21", "remaining_time": "0:37:20"}
+{"current_steps": 1350, "total_steps": 1876, "loss": 0.0767, "accuracy": 0.9781249761581421, "lr": 1.1052768038126466e-06, "epoch": 1.4380495603517187, "percentage": 71.96, "elapsed_time": "1:34:02", "remaining_time": "0:36:38"}
+{"current_steps": 1360, "total_steps": 1876, "loss": 0.1127, "accuracy": 0.956250011920929, "lr": 1.0669060045014216e-06, "epoch": 1.4487077005062616, "percentage": 72.49, "elapsed_time": "1:34:43", "remaining_time": "0:35:56"}
+{"current_steps": 1370, "total_steps": 1876, "loss": 0.0949, "accuracy": 0.9624999761581421, "lr": 1.0290315883064259e-06, "epoch": 1.4593658406608048, "percentage": 73.03, "elapsed_time": "1:35:25", "remaining_time": "0:35:14"}
+{"current_steps": 1380, "total_steps": 1876, "loss": 0.0847, "accuracy": 0.9812500476837158, "lr": 9.9166667385128e-07, "epoch": 1.4700239808153477, "percentage": 73.56, "elapsed_time": "1:36:08", "remaining_time": "0:34:33"}
+{"current_steps": 1390, "total_steps": 1876, "loss": 0.1361, "accuracy": 0.9437500238418579, "lr": 9.54824203282647e-07, "epoch": 1.4806821209698908, "percentage": 74.09, "elapsed_time": "1:36:49", "remaining_time": "0:33:51"}
+{"current_steps": 1400, "total_steps": 1876, "loss": 0.0922, "accuracy": 0.971875011920929, "lr": 9.185169377874489e-07, "epoch": 1.4913402611244337, "percentage": 74.63, "elapsed_time": "1:37:30", "remaining_time": "0:33:09"}
+{"current_steps": 1410, "total_steps": 1876, "loss": 0.0715, "accuracy": 0.9937499761581421, "lr": 8.827574531727454e-07, "epoch": 1.5019984012789767, "percentage": 75.16, "elapsed_time": "1:38:10", "remaining_time": "0:32:26"}
+{"current_steps": 1420, "total_steps": 1876, "loss": 0.1299, "accuracy": 0.9656250476837158, "lr": 8.47558135509838e-07, "epoch": 1.5126565414335198, "percentage": 75.69, "elapsed_time": "1:38:52", "remaining_time": "0:31:44"}
+{"current_steps": 1430, "total_steps": 1876, "loss": 0.0901, "accuracy": 0.96875, "lr": 8.129311768440809e-07, "epoch": 1.523314681588063, "percentage": 76.23, "elapsed_time": "1:39:33", "remaining_time": "0:31:02"}
+{"current_steps": 1440, "total_steps": 1876, "loss": 0.0951, "accuracy": 0.96875, "lr": 7.788885709719035e-07, "epoch": 1.5339728217426059, "percentage": 76.76, "elapsed_time": "1:40:13", "remaining_time": "0:30:20"}
+{"current_steps": 1450, "total_steps": 1876, "loss": 0.103, "accuracy": 0.956250011920929, "lr": 7.454421092865039e-07, "epoch": 1.544630961897149, "percentage": 77.29, "elapsed_time": "1:40:54", "remaining_time": "0:29:38"}
+{"current_steps": 1460, "total_steps": 1876, "loss": 0.0856, "accuracy": 0.981249988079071, "lr": 7.126033766936366e-07, "epoch": 1.5552891020516921, "percentage": 77.83, "elapsed_time": "1:41:36", "remaining_time": "0:28:57"}
+{"current_steps": 1470, "total_steps": 1876, "loss": 0.1007, "accuracy": 0.971875011920929, "lr": 6.80383747598938e-07, "epoch": 1.565947242206235, "percentage": 78.36, "elapsed_time": "1:42:16", "remaining_time": "0:28:14"}
+{"current_steps": 1480, "total_steps": 1876, "loss": 0.1048, "accuracy": 0.9687500596046448, "lr": 6.487943819681489e-07, "epoch": 1.576605382360778, "percentage": 78.89, "elapsed_time": "1:42:58", "remaining_time": "0:27:33"}
+{"current_steps": 1490, "total_steps": 1876, "loss": 0.0789, "accuracy": 0.9781249761581421, "lr": 6.178462214616205e-07, "epoch": 1.587263522515321, "percentage": 79.42, "elapsed_time": "1:43:38", "remaining_time": "0:26:50"}
+{"current_steps": 1500, "total_steps": 1876, "loss": 0.1112, "accuracy": 0.9624999761581421, "lr": 5.875499856444358e-07, "epoch": 1.5979216626698642, "percentage": 79.96, "elapsed_time": "1:44:17", "remaining_time": "0:26:08"}
+{"current_steps": 1500, "total_steps": 1876, "eval_loss": 0.5428091883659363, "epoch": 1.5979216626698642, "percentage": 79.96, "elapsed_time": "1:44:33", "remaining_time": "0:26:12"}
+{"current_steps": 1510, "total_steps": 1876, "loss": 0.0932, "accuracy": 0.971875011920929, "lr": 5.579161682734549e-07, "epoch": 1.6085798028244072, "percentage": 80.49, "elapsed_time": "1:45:15", "remaining_time": "0:25:30"}
+{"current_steps": 1520, "total_steps": 1876, "loss": 0.0746, "accuracy": 0.9874999523162842, "lr": 5.289550336625732e-07, "epoch": 1.61923794297895, "percentage": 81.02, "elapsed_time": "1:45:55", "remaining_time": "0:24:48"}
+{"current_steps": 1530, "total_steps": 1876, "loss": 0.0753, "accuracy": 0.981249988079071, "lr": 5.00676613127456e-07, "epoch": 1.6298960831334932, "percentage": 81.56, "elapsed_time": "1:46:37", "remaining_time": "0:24:06"}
+{"current_steps": 1540, "total_steps": 1876, "loss": 0.0689, "accuracy": 0.981249988079071, "lr": 4.730907015109759e-07, "epoch": 1.6405542232880364, "percentage": 82.09, "elapsed_time": "1:47:22", "remaining_time": "0:23:25"}
+{"current_steps": 1550, "total_steps": 1876, "loss": 0.0919, "accuracy": 0.9781250357627869, "lr": 4.462068537905559e-07, "epoch": 1.6512123634425793, "percentage": 82.62, "elapsed_time": "1:48:04", "remaining_time": "0:22:43"}
+{"current_steps": 1560, "total_steps": 1876, "loss": 0.1161, "accuracy": 0.96875, "lr": 4.200343817685981e-07, "epoch": 1.6618705035971222, "percentage": 83.16, "elapsed_time": "1:48:42", "remaining_time": "0:22:01"}
+{"current_steps": 1570, "total_steps": 1876, "loss": 0.0914, "accuracy": 0.981249988079071, "lr": 3.9458235084713526e-07, "epoch": 1.6725286437516653, "percentage": 83.69, "elapsed_time": "1:49:26", "remaining_time": "0:21:19"}
+{"current_steps": 1580, "total_steps": 1876, "loss": 0.0908, "accuracy": 0.9749999642372131, "lr": 3.698595768878363e-07, "epoch": 1.6831867839062085, "percentage": 84.22, "elapsed_time": "1:50:09", "remaining_time": "0:20:38"}
+{"current_steps": 1590, "total_steps": 1876, "loss": 0.1218, "accuracy": 0.9593750238418579, "lr": 3.4587462315844143e-07, "epoch": 1.6938449240607514, "percentage": 84.75, "elapsed_time": "1:50:50", "remaining_time": "0:19:56"}
+{"current_steps": 1600, "total_steps": 1876, "loss": 0.0948, "accuracy": 0.9750000238418579, "lr": 3.226357973666888e-07, "epoch": 1.7045030642152943, "percentage": 85.29, "elapsed_time": "1:51:33", "remaining_time": "0:19:14"}
+{"current_steps": 1610, "total_steps": 1876, "loss": 0.0717, "accuracy": 0.9750000238418579, "lr": 3.0015114878275827e-07, "epoch": 1.7151612043698374, "percentage": 85.82, "elapsed_time": "1:52:14", "remaining_time": "0:18:32"}
+{"current_steps": 1620, "total_steps": 1876, "loss": 0.1034, "accuracy": 0.96875, "lr": 2.784284654512351e-07, "epoch": 1.7258193445243806, "percentage": 86.35, "elapsed_time": "1:52:55", "remaining_time": "0:17:50"}
+{"current_steps": 1630, "total_steps": 1876, "loss": 0.1123, "accuracy": 0.956250011920929, "lr": 2.574752714935502e-07, "epoch": 1.7364774846789235, "percentage": 86.89, "elapsed_time": "1:53:37", "remaining_time": "0:17:08"}
+{"current_steps": 1640, "total_steps": 1876, "loss": 0.139, "accuracy": 0.940625011920929, "lr": 2.372988245018401e-07, "epoch": 1.7471356248334664, "percentage": 87.42, "elapsed_time": "1:54:18", "remaining_time": "0:16:26"}
+{"current_steps": 1650, "total_steps": 1876, "loss": 0.0803, "accuracy": 0.9812500476837158, "lr": 2.1790611302512115e-07, "epoch": 1.7577937649880095, "percentage": 87.95, "elapsed_time": "1:55:00", "remaining_time": "0:15:45"}
+{"current_steps": 1660, "total_steps": 1876, "loss": 0.1062, "accuracy": 0.9562500715255737, "lr": 1.9930385414865388e-07, "epoch": 1.7684519051425527, "percentage": 88.49, "elapsed_time": "1:55:40", "remaining_time": "0:15:03"}
+{"current_steps": 1670, "total_steps": 1876, "loss": 0.1, "accuracy": 0.9687500596046448, "lr": 1.8149849116733674e-07, "epoch": 1.7791100452970956, "percentage": 89.02, "elapsed_time": "1:56:20", "remaining_time": "0:14:21"}
+{"current_steps": 1680, "total_steps": 1876, "loss": 0.0969, "accuracy": 0.9750000238418579, "lr": 1.6449619135393086e-07, "epoch": 1.7897681854516387, "percentage": 89.55, "elapsed_time": "1:57:01", "remaining_time": "0:13:39"}
+{"current_steps": 1690, "total_steps": 1876, "loss": 0.0959, "accuracy": 0.9750000238418579, "lr": 1.4830284382289146e-07, "epoch": 1.8004263256061819, "percentage": 90.09, "elapsed_time": "1:57:43", "remaining_time": "0:12:57"}
+{"current_steps": 1700, "total_steps": 1876, "loss": 0.1557, "accuracy": 0.9406250715255737, "lr": 1.329240574905452e-07, "epoch": 1.8110844657607248, "percentage": 90.62, "elapsed_time": "1:58:23", "remaining_time": "0:12:15"}
+{"current_steps": 1710, "total_steps": 1876, "loss": 0.1111, "accuracy": 0.96875, "lr": 1.1836515913232178e-07, "epoch": 1.8217426059152677, "percentage": 91.15, "elapsed_time": "1:59:03", "remaining_time": "0:11:33"}
+{"current_steps": 1720, "total_steps": 1876, "loss": 0.0818, "accuracy": 0.9750000238418579, "lr": 1.0463119153770989e-07, "epoch": 1.8324007460698108, "percentage": 91.68, "elapsed_time": "1:59:45", "remaining_time": "0:10:51"}
+{"current_steps": 1730, "total_steps": 1876, "loss": 0.1076, "accuracy": 0.9656250476837158, "lr": 9.172691176357635e-08, "epoch": 1.843058886224354, "percentage": 92.22, "elapsed_time": "2:00:26", "remaining_time": "0:10:09"}
+{"current_steps": 1740, "total_steps": 1876, "loss": 0.0933, "accuracy": 0.96875, "lr": 7.965678948645833e-08, "epoch": 1.853717026378897, "percentage": 92.75, "elapsed_time": "2:01:06", "remaining_time": "0:09:27"}
+{"current_steps": 1750, "total_steps": 1876, "loss": 0.1044, "accuracy": 0.9750000238418579, "lr": 6.84250054543928e-08, "epoch": 1.8643751665334398, "percentage": 93.28, "elapsed_time": "2:01:46", "remaining_time": "0:08:46"}
+{"current_steps": 1760, "total_steps": 1876, "loss": 0.0811, "accuracy": 0.9781250357627869, "lr": 5.803545003882555e-08, "epoch": 1.875033306687983, "percentage": 93.82, "elapsed_time": "2:02:29", "remaining_time": "0:08:04"}
+{"current_steps": 1770, "total_steps": 1876, "loss": 0.1112, "accuracy": 0.9531250596046448, "lr": 4.849172188709589e-08, "epoch": 1.885691446842526, "percentage": 94.35, "elapsed_time": "2:03:10", "remaining_time": "0:07:22"}
+{"current_steps": 1780, "total_steps": 1876, "loss": 0.1202, "accuracy": 0.9625000357627869, "lr": 3.979712667596669e-08, "epoch": 1.896349586997069, "percentage": 94.88, "elapsed_time": "2:03:50", "remaining_time": "0:06:40"}
+{"current_steps": 1790, "total_steps": 1876, "loss": 0.1194, "accuracy": 0.965624988079071, "lr": 3.195467596663254e-08, "epoch": 1.907007727151612, "percentage": 95.42, "elapsed_time": "2:04:34", "remaining_time": "0:05:59"}
+{"current_steps": 1800, "total_steps": 1876, "loss": 0.0802, "accuracy": 0.9750000238418579, "lr": 2.496708616160082e-08, "epoch": 1.917665867306155, "percentage": 95.95, "elapsed_time": "2:05:15", "remaining_time": "0:05:17"}
+{"current_steps": 1810, "total_steps": 1876, "loss": 0.1006, "accuracy": 0.9531250596046448, "lr": 1.883677756380542e-08, "epoch": 1.9283240074606982, "percentage": 96.48, "elapsed_time": "2:05:56", "remaining_time": "0:04:35"}
+{"current_steps": 1820, "total_steps": 1876, "loss": 0.0858, "accuracy": 0.9781250357627869, "lr": 1.3565873538283758e-08, "epoch": 1.9389821476152411, "percentage": 97.01, "elapsed_time": "2:06:39", "remaining_time": "0:03:53"}
+{"current_steps": 1830, "total_steps": 1876, "loss": 0.0814, "accuracy": 0.9812500476837158, "lr": 9.156199776702567e-09, "epoch": 1.949640287769784, "percentage": 97.55, "elapsed_time": "2:07:20", "remaining_time": "0:03:12"}
+{"current_steps": 1840, "total_steps": 1876, "loss": 0.1013, "accuracy": 0.9656250476837158, "lr": 5.609283664990694e-09, "epoch": 1.9602984279243272, "percentage": 98.08, "elapsed_time": "2:08:01", "remaining_time": "0:02:30"}
+{"current_steps": 1850, "total_steps": 1876, "loss": 0.1104, "accuracy": 0.9562500715255737, "lr": 2.9263537542958962e-09, "epoch": 1.9709565680788703, "percentage": 98.61, "elapsed_time": "2:08:41", "remaining_time": "0:01:48"}
+{"current_steps": 1860, "total_steps": 1876, "loss": 0.1063, "accuracy": 0.9593749642372131, "lr": 1.1083393354488492e-09, "epoch": 1.9816147082334132, "percentage": 99.15, "elapsed_time": "2:09:23", "remaining_time": "0:01:06"}
+{"current_steps": 1870, "total_steps": 1876, "loss": 0.0837, "accuracy": 0.984375, "lr": 1.5587011708340093e-10, "epoch": 1.9922728483879562, "percentage": 99.68, "elapsed_time": "2:10:04", "remaining_time": "0:00:25"}
+{"current_steps": 1876, "total_steps": 1876, "epoch": 1.998667732480682, "percentage": 100.0, "elapsed_time": "2:10:50", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21dec6ff80abdb2c00deb85899f6c80705f0a92cd37439fc8d521af4eeaa396
+size 7544