Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f305e461acf943633d5ccd25974c8fe15a461d418887eb749e9db5534daec5
+oid sha256:d4fa93565cff642ee223b46502df77abd126352a7d3b926d12b1fa8aaff201bd
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f9599a9a6e619887065f7c24cb3b027bb5797bdab880af8ba3ea4221511c22
+oid sha256:95add27b4bc4dd443bff40a096f0111bea14534d1319bc9ee3e974ccacaf3fb9
 size 41119636

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": 0.07073386383731212,
+  "epoch": 0.14146772767462423,
   "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": 20.631,
       "eval_steps_per_second": 10.316,
       "step": 5
+    },
+    {
+      "epoch": 0.08488063660477453,
+      "grad_norm": 5.7256669998168945,
+      "learning_rate": 6e-05,
+      "loss": 7.4766,
+      "step": 6
+    },
+    {
+      "epoch": 0.09902740937223696,
+      "grad_norm": 5.811617374420166,
+      "learning_rate": 7e-05,
+      "loss": 7.0652,
+      "step": 7
+    },
+    {
+      "epoch": 0.11317418213969938,
+      "grad_norm": 6.549645900726318,
+      "learning_rate": 8e-05,
+      "loss": 6.8741,
+      "step": 8
+    },
+    {
+      "epoch": 0.1273209549071618,
+      "grad_norm": 7.107234477996826,
+      "learning_rate": 9e-05,
+      "loss": 6.21,
+      "step": 9
+    },
+    {
+      "epoch": 0.14146772767462423,
+      "grad_norm": 6.856642246246338,
+      "learning_rate": 0.0001,
+      "loss": 5.349,
+      "step": 10
+    },
+    {
+      "epoch": 0.14146772767462423,
+      "eval_loss": 4.707101345062256,
+      "eval_runtime": 5.8383,
+      "eval_samples_per_second": 20.554,
+      "eval_steps_per_second": 10.277,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3378036992901120.0,
+  "total_flos": 6714878412718080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null