Training in progress, step 30500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8367a24eb06a34cbf04ec05d49423cacadb43f1fbc7c9b46cd3bc8f7d202aeea
+oid sha256:f0b4d2a21ab34ea5aae19f2c79c17d535d0eceb21e9bd3fbe132c0c6743fbd74
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69cfb99a1d47731eb0bd0f0aa8008f24af3b21461df86591e07ee79decd04b36
+oid sha256:60601e0df9ec0d20e49569fddd22a460360511cad0bf70986d2e0dfe2c6fc5ac
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59297a887ee86d9ae2f8461a820add9f102e062ed6b208e7b0f014f86659cc1d
+oid sha256:cbfe40bf67dcc41ade516e25138c73f55e1a79032c0542ad6be33784e59a5c69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ece32524ff12cd47152c7073cf4a24f61bf2d3f6e989a1d942aaad706c29e5e
+oid sha256:a6148692faa22908e20b6fbcdb986515b0d89f409366c21a08301b9100cfff4f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 2.033333333333333,
   "eval_steps": 500,
-  "global_step": 30000,
+  "global_step": 30500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2115,6 +2115,49 @@
       "learning_rate": 6.671555555555556e-06,
       "loss": 0.0569,
       "step": 30000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.08315848559141159,
+      "eval_runtime": 120.1805,
+      "eval_samples_per_second": 16.642,
+      "eval_steps_per_second": 4.16,
+      "step": 30000
+    },
+    {
+      "epoch": 2.006666666666667,
+      "grad_norm": 0.2182902991771698,
+      "learning_rate": 6.627111111111112e-06,
+      "loss": 0.0532,
+      "step": 30100
+    },
+    {
+      "epoch": 2.013333333333333,
+      "grad_norm": 0.2302951216697693,
+      "learning_rate": 6.582666666666667e-06,
+      "loss": 0.0551,
+      "step": 30200
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.25131645798683167,
+      "learning_rate": 6.538222222222222e-06,
+      "loss": 0.0531,
+      "step": 30300
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 0.2000693827867508,
+      "learning_rate": 6.493777777777779e-06,
+      "loss": 0.055,
+      "step": 30400
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.2072344422340393,
+      "learning_rate": 6.4493333333333345e-06,
+      "loss": 0.0544,
+      "step": 30500
     }
   ],
   "logging_steps": 100,
@@ -2134,7 +2177,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.30749468672e+16,
+  "total_flos": 7.429286264832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null