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:c8d8d6565625d34cacfc7de38f6c0ac2697d54e3a288671727d121b78795c725
+oid sha256:79fa7292ec3339d47d01c9f35abef8c0f37d9c8b2099ce1bbf44d7d134145708
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1389778ec3ded5ecbb78ce3786fabe0343b7487b1b65e5930e375633ab5a05f
+oid sha256:81e323c9813aa92a2735409d8fb572a842942fd8d9ea5bb07c44a46b751c9602
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7823b6a88a1bff551f35584ad7d670f13fc55c997cc4bc062fed88c0ad789aba
+oid sha256:0e1f723b1b444822d3cfd3428b6b6499afae41cfad9d0785da532b98ec65f179
 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": 0.028145229383619477,
+  "epoch": 0.03752697251149264,
   "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": 9.055,
       "eval_steps_per_second": 4.528,
       "step": 150
+    },
+    {
+      "epoch": 0.030021578009194107,
+      "grad_norm": 0.9416802525520325,
+      "learning_rate": 0.0002,
+      "loss": 1.9475,
+      "step": 160
+    },
+    {
+      "epoch": 0.03189792663476874,
+      "grad_norm": 1.1194655895233154,
+      "learning_rate": 0.0002,
+      "loss": 2.1873,
+      "step": 170
+    },
+    {
+      "epoch": 0.03377427526034337,
+      "grad_norm": 0.871798574924469,
+      "learning_rate": 0.0002,
+      "loss": 1.8437,
+      "step": 180
+    },
+    {
+      "epoch": 0.035650623885918005,
+      "grad_norm": 2.2867114543914795,
+      "learning_rate": 0.0002,
+      "loss": 1.9248,
+      "step": 190
+    },
+    {
+      "epoch": 0.03752697251149264,
+      "grad_norm": 0.9505456686019897,
+      "learning_rate": 0.0002,
+      "loss": 2.219,
+      "step": 200
+    },
+    {
+      "epoch": 0.03752697251149264,
+      "eval_loss": 0.4897903800010681,
+      "eval_runtime": 248.0094,
+      "eval_samples_per_second": 9.048,
+      "eval_steps_per_second": 4.524,
+      "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": 9.70797724729344e+16,
+  "total_flos": 1.298643675512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null