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:b69b2deefef688bd0f64ef526ebf6ee804b25a034c4f7b436eab9ae4f9478e1e
+oid sha256:d078e43505dfe4719a7b5b3d7872229a9e161bce7ee442e399fe2e11a81a4e66
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d7dc2ef86adc6df4c2d3d54bb22c623324b436c257672f3373f3a50f25aefe
+oid sha256:37f73a026f03da663aecf168248b10a5a959fccc92f4d62375493dd9ebad3972
 size 13685516

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": 0.14109347442680775,
+  "epoch": 0.2821869488536155,
   "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": 123.04,
       "eval_steps_per_second": 61.52,
       "step": 5
+    },
+    {
+      "epoch": 0.1693121693121693,
+      "grad_norm": 1.918559193611145,
+      "learning_rate": 6e-05,
+      "loss": 6.5218,
+      "step": 6
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 2.5789589881896973,
+      "learning_rate": 7e-05,
+      "loss": 6.2126,
+      "step": 7
+    },
+    {
+      "epoch": 0.2257495590828924,
+      "grad_norm": 2.5044870376586914,
+      "learning_rate": 8e-05,
+      "loss": 6.2001,
+      "step": 8
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 2.7968616485595703,
+      "learning_rate": 9e-05,
+      "loss": 6.5004,
+      "step": 9
+    },
+    {
+      "epoch": 0.2821869488536155,
+      "grad_norm": 2.528766393661499,
+      "learning_rate": 0.0001,
+      "loss": 6.0157,
+      "step": 10
+    },
+    {
+      "epoch": 0.2821869488536155,
+      "eval_loss": 5.689663887023926,
+      "eval_runtime": 0.4947,
+      "eval_samples_per_second": 121.289,
+      "eval_steps_per_second": 60.645,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 511583956500480.0,
+  "total_flos": 1023167913000960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null