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:a8526857e439ccded547faf4e04e6c50bd16b2abe44c011ad06191a88d94c930
+oid sha256:39bdde0c8688c4d8adddfb4d4f3c752729d7673b18eb9ec1278c173fdf995c30
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3583d7424ca89f63255c5e695b9b9810c7e82d1e13771761e058e0c2432b0ed
+oid sha256:4272ff94de1745812aeafcf93024c537f35fcbdfa07bf190c9994eda170d2e24
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a0d178020fecc5513a454227b25f3a8a60c61c1b470c9504f50321e953b23a6
+oid sha256:05186ba87eecce812d7230bcfc512f923a59e6481f8a6aec4d15453085ee1f61
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0297000297000297,
+  "epoch": 0.0396000396000396,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 11.971,
       "eval_steps_per_second": 5.988,
       "step": 150
+    },
+    {
+      "epoch": 0.03168003168003168,
+      "grad_norm": 1.7976691722869873,
+      "learning_rate": 0.0002,
+      "loss": 3.2878,
+      "step": 160
+    },
+    {
+      "epoch": 0.03366003366003366,
+      "grad_norm": 1.4198904037475586,
+      "learning_rate": 0.0002,
+      "loss": 3.3432,
+      "step": 170
+    },
+    {
+      "epoch": 0.03564003564003564,
+      "grad_norm": 1.6277859210968018,
+      "learning_rate": 0.0002,
+      "loss": 3.8561,
+      "step": 180
+    },
+    {
+      "epoch": 0.03762003762003762,
+      "grad_norm": 1.1398273706436157,
+      "learning_rate": 0.0002,
+      "loss": 3.5024,
+      "step": 190
+    },
+    {
+      "epoch": 0.0396000396000396,
+      "grad_norm": 1.2557786703109741,
+      "learning_rate": 0.0002,
+      "loss": 3.0593,
+      "step": 200
+    },
+    {
+      "epoch": 0.0396000396000396,
+      "eval_loss": 0.8267537951469421,
+      "eval_runtime": 177.798,
+      "eval_samples_per_second": 11.963,
+      "eval_steps_per_second": 5.984,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.3218937061376e+16,
+  "total_flos": 9.680730813628416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null