Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6023122ccd03b73b0c9f4fb91456bcb21dbd645450a406438a33cd3ea8ad9c8
+oid sha256:61996341056c0dabfab719a24657f6be2c1701f6ab89a6b0227572c4e5cbfd87
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c6ddf30872d89762dee68250dc32848fa779a7ef2ac5e5b316bf8cd4211850
+oid sha256:71ff81c602eef2b9aea49d39e2dc2325b032b26045cd7cdfca451de5e4ca8984
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df27d9783b9d53c6a7276610bb3af7095069f4390b9601b198099568ccd0bc91
+oid sha256:b632b832bdc839a1f87f2b54a86c7465bc00e10f4d1d0eef845b6f6921a2856e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010767884783632815,
+  "epoch": 0.002153576956726563,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 8.362,
       "eval_steps_per_second": 4.184,
       "step": 4
+    },
+    {
+      "epoch": 0.0013459855979541019,
+      "grad_norm": 6.113898754119873,
+      "learning_rate": 0.0001,
+      "loss": 5.5139,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016151827175449223,
+      "grad_norm": 4.3670973777771,
+      "learning_rate": 0.00012,
+      "loss": 4.8011,
+      "step": 6
+    },
+    {
+      "epoch": 0.0018843798371357427,
+      "grad_norm": 8.779766082763672,
+      "learning_rate": 0.00014,
+      "loss": 4.9951,
+      "step": 7
+    },
+    {
+      "epoch": 0.002153576956726563,
+      "grad_norm": 8.467183113098145,
+      "learning_rate": 0.00016,
+      "loss": 4.8208,
+      "step": 8
+    },
+    {
+      "epoch": 0.002153576956726563,
+      "eval_loss": 4.797426700592041,
+      "eval_runtime": 187.0275,
+      "eval_samples_per_second": 8.368,
+      "eval_steps_per_second": 4.187,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3067577446170624.0,
+  "total_flos": 6135154892341248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null