Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c460049ea29911b8e4b0d918908c4b82cdf5ab18398f05fd3eec4cc9879b02b
+oid sha256:defb1969cb16556fe7416630ce829b4158da2b37d5362a20d2dcee845edc6a50
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e1f79695ac6ce452d93af703df459550ca84c81d243356eaa348d4ff1b6a31d
+oid sha256:6bd9645d561261bced18ee4133b05c8bc917727922a86275eaa7de3f977f5954
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba14db64c9c68d07d7f1a5cb41dae7a5f759419ee176af34ec6fd25083d6a02e
+oid sha256:74e995da13d592c45b9e27483ecb30d98cacbe80c36a84b43e20cbfcfa090f88
 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": 0.026760626198653048,
+  "epoch": 0.0356808349315374,
   "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": 19.82,
       "eval_steps_per_second": 9.914,
       "step": 150
+    },
+    {
+      "epoch": 0.028544667945229918,
+      "grad_norm": 0.46581530570983887,
+      "learning_rate": 0.0002,
+      "loss": 2.3928,
+      "step": 160
+    },
+    {
+      "epoch": 0.030328709691806788,
+      "grad_norm": 0.41251781582832336,
+      "learning_rate": 0.0002,
+      "loss": 2.3686,
+      "step": 170
+    },
+    {
+      "epoch": 0.03211275143838366,
+      "grad_norm": 0.3910543620586395,
+      "learning_rate": 0.0002,
+      "loss": 2.3908,
+      "step": 180
+    },
+    {
+      "epoch": 0.03389679318496053,
+      "grad_norm": 0.46539127826690674,
+      "learning_rate": 0.0002,
+      "loss": 2.407,
+      "step": 190
+    },
+    {
+      "epoch": 0.0356808349315374,
+      "grad_norm": 0.46478888392448425,
+      "learning_rate": 0.0002,
+      "loss": 2.3919,
+      "step": 200
+    },
+    {
+      "epoch": 0.0356808349315374,
+      "eval_loss": 2.406040668487549,
+      "eval_runtime": 119.1228,
+      "eval_samples_per_second": 19.82,
+      "eval_steps_per_second": 9.914,
+      "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": 4.108195366699008e+16,
+  "total_flos": 5.523357780934656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null