Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5bdb38007dafefbe7e40775bc5125f98bdbbc984b7408b5fe3513b07dca0e58
+oid sha256:bb354011d0914f2f261ccf6c9395df0294683444eaaeedbff9b75e5ad0b1af9e
 size 1822093912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00dfae8cea64e102aff5b1794a1a620ce135144c2b65b889e4669ff740dd9f0f
-size 650679452
+oid sha256:0cdff59589c53992007a9e4b93573b3697f05f34a6f54e8cc3b8f62fcda35803
+size 651839518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd94f5d02dc9debc35e13f4d32c2a4c9fb832aa83b3beef539d230a914cdc96
+oid sha256:d8928cd58543f35cda2b5a759e04996998675afef60590edabc32349fcd3ca57
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efdbfe8676cd24a75fed7e6e38125bb1bb838a4b70c0fbf7469557659d9b1fec
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 1.2,
   "eval_steps": 500,
-  "global_step": 125,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,13 +757,163 @@
       "learning_rate": 0.0002,
       "loss": 0.4894,
       "step": 125
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002,
+      "loss": 0.6574,
+      "step": 126
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 0.6102,
+      "step": 127
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 0.5459,
+      "step": 128
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.5237,
+      "step": 129
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002,
+      "loss": 0.5041,
+      "step": 130
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0002,
+      "loss": 0.5344,
+      "step": 131
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002,
+      "loss": 0.5144,
+      "step": 132
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002,
+      "loss": 0.461,
+      "step": 133
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.4629,
+      "step": 134
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0002,
+      "loss": 0.4783,
+      "step": 135
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 0.4263,
+      "step": 136
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0002,
+      "loss": 0.4718,
+      "step": 137
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0002,
+      "loss": 0.4671,
+      "step": 138
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0002,
+      "loss": 0.4783,
+      "step": 139
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0002,
+      "loss": 0.4188,
+      "step": 140
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002,
+      "loss": 0.4106,
+      "step": 141
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002,
+      "loss": 0.4498,
+      "step": 142
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002,
+      "loss": 0.4254,
+      "step": 143
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002,
+      "loss": 0.4038,
+      "step": 144
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002,
+      "loss": 0.3871,
+      "step": 145
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 0.4085,
+      "step": 146
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002,
+      "loss": 0.3769,
+      "step": 147
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002,
+      "loss": 0.4008,
+      "step": 148
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002,
+      "loss": 0.3574,
+      "step": 149
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 0.3183,
+      "step": 150
     }
   ],
   "logging_steps": 1,
-  "max_steps": 125,
-  "num_train_epochs": 1,
+  "max_steps": 250,
+  "num_train_epochs": 2,
   "save_steps": 25,
-  "total_flos": 1.6025387130421248e+16,
+  "total_flos": 1.940920465214669e+16,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd222606e3c42700ba9169f9c89fe58464172118ea988dcde97a15a116396c12
+oid sha256:0a401eaa6e3150c30ceb7df6868b38913d3bec6cde21eeab34c1f292bc4e4ae5
 size 4536