Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d06fc7fc82c638274c137a3afb8932d1600143857c92dfe86b9615bbd912b97
+oid sha256:01006bc04cf644c4a19835b0a939d48ffe913d45a0758d78f6312c6b90f4604d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a17b78f2acfcba4d2b49edaa930f3dd69a648bbcbd66766d0ed5be453619853
+oid sha256:ebf28f1e369d1b6504685edbd02f3cac6d25951f3c2c61d9f862929d3c20977d
 size 43122580

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": 0.017185821697099892,
+  "epoch": 0.034371643394199784,
   "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": 19.829,
       "eval_steps_per_second": 9.915,
       "step": 5
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 1.1580060720443726,
+      "learning_rate": 6e-05,
+      "loss": 2.7856,
+      "step": 6
+    },
+    {
+      "epoch": 0.02406015037593985,
+      "grad_norm": 1.037327527999878,
+      "learning_rate": 7e-05,
+      "loss": 2.7426,
+      "step": 7
+    },
+    {
+      "epoch": 0.02749731471535983,
+      "grad_norm": 1.1322250366210938,
+      "learning_rate": 8e-05,
+      "loss": 2.762,
+      "step": 8
+    },
+    {
+      "epoch": 0.030934479054779807,
+      "grad_norm": 0.8920819759368896,
+      "learning_rate": 9e-05,
+      "loss": 2.6572,
+      "step": 9
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "grad_norm": 0.7211071252822876,
+      "learning_rate": 0.0001,
+      "loss": 2.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "eval_loss": 2.593578577041626,
+      "eval_runtime": 26.2073,
+      "eval_samples_per_second": 18.697,
+      "eval_steps_per_second": 9.349,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3699128496291840.0,
+  "total_flos": 7398256992583680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null