Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4e0b4d82c7a16e4d558b7655e55672a2b6fa4434bd635700cc4c0af4810e8c
+oid sha256:0966af469b96b13c3e8a6d5c711005b5f47557c73256ba1ffcbba5d57f5db5c4
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d2799aae108d3f35376a964df28a8f4c3e40eea36e44314553c98b81b3f6677
+oid sha256:5ec7254b71fe92cd7b890f0f97a3d0b137efafbbe1a7a42bca15ae9f7481ab84
 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:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 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": 11.933,
       "eval_steps_per_second": 5.97,
       "step": 150
+    },
+    {
+      "epoch": 0.03168003168003168,
+      "grad_norm": 1.8658894300460815,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 3.32,
+      "step": 160
+    },
+    {
+      "epoch": 0.03366003366003366,
+      "grad_norm": 1.666367530822754,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 3.3608,
+      "step": 170
+    },
+    {
+      "epoch": 0.03564003564003564,
+      "grad_norm": 1.6707497835159302,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 3.8797,
+      "step": 180
+    },
+    {
+      "epoch": 0.03762003762003762,
+      "grad_norm": 1.3093181848526,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 3.5669,
+      "step": 190
+    },
+    {
+      "epoch": 0.0396000396000396,
+      "grad_norm": 1.2601022720336914,
+      "learning_rate": 0.0,
+      "loss": 3.1048,
+      "step": 200
+    },
+    {
+      "epoch": 0.0396000396000396,
+      "eval_loss": 0.8417183756828308,
+      "eval_runtime": 178.0902,
+      "eval_samples_per_second": 11.943,
+      "eval_steps_per_second": 5.974,
+      "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