Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b698a2b3e4e5058d195e12f09c5e0e9d388b86b4108d7ffb3524ebd7d7768abb
+oid sha256:593171bdc90ce208d1fd8cdc9b93e5460cfb96259ee06fe88cc24bd22e2fc76f
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c011e6451d1878cbc4f7331e8c7c0b9074336a95df4907949f1674a1d623387e
+oid sha256:bf2849f55a3470590db89f50f599b38412f1c1a80260d0237c07b5a236c53df7
 size 3633466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff226c15e19b8085e09f0025aa31f4d46c591e213735b264a5e28d7f9728a70c
+oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008553405324494815,
+  "epoch": 0.01710681064898963,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 257.654,
       "eval_steps_per_second": 128.958,
       "step": 5
+    },
+    {
+      "epoch": 0.010264086389393778,
+      "grad_norm": 0.4884447753429413,
+      "learning_rate": 6e-05,
+      "loss": 3.3282,
+      "step": 6
+    },
+    {
+      "epoch": 0.01197476745429274,
+      "grad_norm": 0.5128330588340759,
+      "learning_rate": 7e-05,
+      "loss": 3.3899,
+      "step": 7
+    },
+    {
+      "epoch": 0.013685448519191703,
+      "grad_norm": 0.4853476583957672,
+      "learning_rate": 8e-05,
+      "loss": 3.4673,
+      "step": 8
+    },
+    {
+      "epoch": 0.015396129584090666,
+      "grad_norm": 0.4155305325984955,
+      "learning_rate": 9e-05,
+      "loss": 3.1119,
+      "step": 9
+    },
+    {
+      "epoch": 0.01710681064898963,
+      "grad_norm": 0.5410354733467102,
+      "learning_rate": 0.0001,
+      "loss": 3.4547,
+      "step": 10
+    },
+    {
+      "epoch": 0.01710681064898963,
+      "eval_loss": 3.410022020339966,
+      "eval_runtime": 3.9919,
+      "eval_samples_per_second": 246.751,
+      "eval_steps_per_second": 123.501,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 68585300951040.0,
+  "total_flos": 137170601902080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null