Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75f0be281ea1cbfe926fd1278c9fa608b1a3afac19c94e56b924c14a170959c6
+oid sha256:3f393a783ccd01583f94a7530b7a1a084d27984eacf5d9836047851c3e083b3e
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e880217f1e2ce6478d761e72a6ba089e2d640ba603f3658c21d93961dd28b5
+oid sha256:7c29127f46d9c4c88b8ef54ad7a1b13c375207cb9f1691aa4906c5580bf9d700
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85dc3b6b108465bb3f0d2123d2d7eb1590c104f1271fcf1606388519934975bf
+oid sha256:3f3fe9056168231b617b0616dc0a99f0dd35b8ab4b7f503dda82b38934c1a8d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f794552decd9aa76ab29a20764126af04a4c938707d8fa5c1d538d8352460007
+oid sha256:5256258c422cade61a05f9b7acf2463558d18db9447187b4d8690b3bca3e867f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003956292388847023,
+  "epoch": 0.0073474001507159,
   "eval_steps": 5,
-  "global_step": 21,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -96,6 +96,72 @@
       "learning_rate": 0.0002,
       "loss": 14.1356,
       "step": 21
+    },
+    {
+      "epoch": 0.00452147701582517,
+      "grad_norm": 10.909833908081055,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 14.5539,
+      "step": 24
+    },
+    {
+      "epoch": 0.004709871891484552,
+      "eval_loss": 3.477104425430298,
+      "eval_runtime": 93.6445,
+      "eval_samples_per_second": 23.867,
+      "eval_steps_per_second": 11.939,
+      "step": 25
+    },
+    {
+      "epoch": 0.005086661642803316,
+      "grad_norm": 8.179487228393555,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 13.8681,
+      "step": 27
+    },
+    {
+      "epoch": 0.005651846269781462,
+      "grad_norm": 13.335248947143555,
+      "learning_rate": 0.0001,
+      "loss": 13.9842,
+      "step": 30
+    },
+    {
+      "epoch": 0.005651846269781462,
+      "eval_loss": 3.4619498252868652,
+      "eval_runtime": 93.6229,
+      "eval_samples_per_second": 23.872,
+      "eval_steps_per_second": 11.942,
+      "step": 30
+    },
+    {
+      "epoch": 0.0062170308967596085,
+      "grad_norm": 38.59743118286133,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 14.0316,
+      "step": 33
+    },
+    {
+      "epoch": 0.0065938206480783725,
+      "eval_loss": 3.4556496143341064,
+      "eval_runtime": 93.6059,
+      "eval_samples_per_second": 23.877,
+      "eval_steps_per_second": 11.944,
+      "step": 35
+    },
+    {
+      "epoch": 0.006782215523737754,
+      "grad_norm": 4.950757026672363,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 14.2708,
+      "step": 36
+    },
+    {
+      "epoch": 0.0073474001507159,
+      "grad_norm": 54.93941879272461,
+      "learning_rate": 0.0,
+      "loss": 13.8209,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -110,12 +176,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 364045186105344.0,
+  "total_flos": 697753273368576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null