Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d27c456f14de4b1b6a36bbb41f01e2deb0fc705771a113fd696ef9a6ec27089
+oid sha256:3ad8ba44ccf1a7a92b8762ece327844da80e1e40d1ec4dd0caa287ee452a8f3a
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601a47b4aea211e3fcb37a8deae01205dac231883ea531e410a8a2be15750457
+oid sha256:7cad986c13d362c5b15c9751050b62b4ee254c4bd6416a588ea54705d9e9847b
 size 39398

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": 0.013736263736263736,
+  "epoch": 0.027472527472527472,
   "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": 693.681,
       "eval_steps_per_second": 346.84,
       "step": 5
+    },
+    {
+      "epoch": 0.016483516483516484,
+      "grad_norm": 0.015183483250439167,
+      "learning_rate": 6e-05,
+      "loss": 11.9311,
+      "step": 6
+    },
+    {
+      "epoch": 0.019230769230769232,
+      "grad_norm": 0.01923339068889618,
+      "learning_rate": 7e-05,
+      "loss": 11.9326,
+      "step": 7
+    },
+    {
+      "epoch": 0.02197802197802198,
+      "grad_norm": 0.01614537090063095,
+      "learning_rate": 8e-05,
+      "loss": 11.932,
+      "step": 8
+    },
+    {
+      "epoch": 0.024725274725274724,
+      "grad_norm": 0.015101440250873566,
+      "learning_rate": 9e-05,
+      "loss": 11.9324,
+      "step": 9
+    },
+    {
+      "epoch": 0.027472527472527472,
+      "grad_norm": 0.016025038436055183,
+      "learning_rate": 0.0001,
+      "loss": 11.9315,
+      "step": 10
+    },
+    {
+      "epoch": 0.027472527472527472,
+      "eval_loss": 11.931865692138672,
+      "eval_runtime": 0.9628,
+      "eval_samples_per_second": 637.728,
+      "eval_steps_per_second": 318.864,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2363228160.0,
+  "total_flos": 4726456320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null