Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb21d37b2c6013186bf804680d0895d1771aed25e307f813b1f393f4706849a
+oid sha256:09cdf31a7149549e7c47d2693a06edb140167fcfb7f50d08147f05fb5fa08626
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ab28a564619cdeae236acfc0650bbdab2a1c83909a7b5df219b8452c237c7a
+oid sha256:9bc3f7d4f6e65f879f5eabcfa452ee547ac39c99a4a5a154fcdf2dbf67a6511e
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:688772f6d19d70f72936e995a93026bfb9abc712a36d67097873a85f49682fa8
+oid sha256:50c8f9662444a91e91f01d69a445b49517e278e5e03e01795aa31274466481e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7708307d1b959a393541df6c657dca87476d08205aaca5feb82f751cfc227436
+oid sha256:93a4031351d40494c6fa2a2ab0690336e71553ec331e91c1b2ab832fe81468d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.184658408164978,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0022987184644560656,
+  "best_metric": 1.1274107694625854,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.004597436928912131,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 35.22,
       "eval_steps_per_second": 17.611,
       "step": 100
+    },
+    {
+      "epoch": 0.0025285903109016723,
+      "grad_norm": 3.7343056201934814,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 1.0981,
+      "step": 110
+    },
+    {
+      "epoch": 0.002758462157347279,
+      "grad_norm": 4.652059078216553,
+      "learning_rate": 3e-05,
+      "loss": 1.2341,
+      "step": 120
+    },
+    {
+      "epoch": 0.0029883340037928853,
+      "grad_norm": 4.9458231925964355,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 1.1237,
+      "step": 130
+    },
+    {
+      "epoch": 0.003218205850238492,
+      "grad_norm": 3.449315309524536,
+      "learning_rate": 3.5e-05,
+      "loss": 1.0449,
+      "step": 140
+    },
+    {
+      "epoch": 0.0034480776966840988,
+      "grad_norm": 4.949376106262207,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.1911,
+      "step": 150
+    },
+    {
+      "epoch": 0.003677949543129705,
+      "grad_norm": 5.409412384033203,
+      "learning_rate": 4e-05,
+      "loss": 1.0661,
+      "step": 160
+    },
+    {
+      "epoch": 0.003907821389575312,
+      "grad_norm": 3.166673421859741,
+      "learning_rate": 4.25e-05,
+      "loss": 1.1751,
+      "step": 170
+    },
+    {
+      "epoch": 0.0041376932360209185,
+      "grad_norm": 3.628138303756714,
+      "learning_rate": 4.5e-05,
+      "loss": 1.1335,
+      "step": 180
+    },
+    {
+      "epoch": 0.004367565082466525,
+      "grad_norm": 3.710859775543213,
+      "learning_rate": 4.75e-05,
+      "loss": 1.1087,
+      "step": 190
+    },
+    {
+      "epoch": 0.004597436928912131,
+      "grad_norm": 3.711989164352417,
+      "learning_rate": 5e-05,
+      "loss": 1.2195,
+      "step": 200
+    },
+    {
+      "epoch": 0.004597436928912131,
+      "eval_loss": 1.1274107694625854,
+      "eval_runtime": 521.4205,
+      "eval_samples_per_second": 35.129,
+      "eval_steps_per_second": 17.565,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.06657392623616e+16,
+  "total_flos": 2.13314785247232e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null