Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f3b7738be84d85e62cafcb47b12ad70607aaa109e75db223026f9907d8d124
+oid sha256:21158e0839814d1acceb8eec657e1aa0ff410daf2da01ae70f40559968e90504
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded39b99e854ea80ea482f4939d531e8368f51f2b513f393a7ca0ba2565f64b4
+oid sha256:b58aa98947e9e9bb68638f73284d326a2e29e1ae91120aedefbb471d4c9acc1e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:696db754cc9c7f647498664de519769d86927bc1db476712736bf9f6a83925a2
+oid sha256:4be7269414a4e70f7ae9ff3693b19985274f38f7a83a725c6b7ecdd541270894
 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": 0.28116213683223995,
+  "epoch": 0.37488284910965325,
   "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": 10.757,
       "eval_steps_per_second": 5.402,
       "step": 150
+    },
+    {
+      "epoch": 0.29990627928772257,
+      "grad_norm": 0.5619802474975586,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 1.7465,
+      "step": 160
+    },
+    {
+      "epoch": 0.31865042174320524,
+      "grad_norm": 0.5154170989990234,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.7235,
+      "step": 170
+    },
+    {
+      "epoch": 0.3373945641986879,
+      "grad_norm": 0.4693893492221832,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.6667,
+      "step": 180
+    },
+    {
+      "epoch": 0.3561387066541706,
+      "grad_norm": 0.5038012862205505,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 1.6542,
+      "step": 190
+    },
+    {
+      "epoch": 0.37488284910965325,
+      "grad_norm": 0.47858622670173645,
+      "learning_rate": 0.0,
+      "loss": 1.7243,
+      "step": 200
+    },
+    {
+      "epoch": 0.37488284910965325,
+      "eval_loss": NaN,
+      "eval_runtime": 20.9093,
+      "eval_samples_per_second": 10.761,
+      "eval_steps_per_second": 5.404,
+      "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": 9.308643967107072e+16,
+  "total_flos": 1.2395694262321152e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null