Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c04b0e443e51c7f8d681f95d4e25a99897b4da9f7850c12d22b70cef07ea234
+oid sha256:537e4ac64c5968a7128773d1fe8d0186b679f5880fdf7acf6261a84c3074691b
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af3df23a8d0cdb522bf1f3e4c413b7245580657b46c7572152c5c77532c9d6f
+oid sha256:f8a972df162fe40030d93bb663e575f6238e7c87c888bf0733557d2ac645f5e1
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
+oid sha256:70bb08e79cd87e26411515d4cfe540a1dfafd998745c321dfb4680b9ed334a58
 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": 0.0274310794129749,
+  "epoch": 0.036574772550633204,
   "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": 327.454,
       "eval_steps_per_second": 163.798,
       "step": 150
+    },
+    {
+      "epoch": 0.02925981804050656,
+      "grad_norm": 0.16217245161533356,
+      "learning_rate": 0.0002,
+      "loss": 10.3289,
+      "step": 160
+    },
+    {
+      "epoch": 0.031088556668038222,
+      "grad_norm": 0.16884753108024597,
+      "learning_rate": 0.0002,
+      "loss": 10.33,
+      "step": 170
+    },
+    {
+      "epoch": 0.03291729529556988,
+      "grad_norm": 0.14734669029712677,
+      "learning_rate": 0.0002,
+      "loss": 10.328,
+      "step": 180
+    },
+    {
+      "epoch": 0.03474603392310154,
+      "grad_norm": 0.12500721216201782,
+      "learning_rate": 0.0002,
+      "loss": 10.3297,
+      "step": 190
+    },
+    {
+      "epoch": 0.036574772550633204,
+      "grad_norm": 0.14943064749240875,
+      "learning_rate": 0.0002,
+      "loss": 10.3302,
+      "step": 200
+    },
+    {
+      "epoch": 0.036574772550633204,
+      "eval_loss": 10.322860717773438,
+      "eval_runtime": 6.7929,
+      "eval_samples_per_second": 339.029,
+      "eval_steps_per_second": 169.588,
+      "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": 3426690662400.0,
+  "total_flos": 4558145126400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null