Training in progress, step 38500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b01c6e320f3b8ce398fbd50bb34cd5deb4150ad4b0e09a91d304d07ef6a1d44
+oid sha256:61083c956d931fcb4b0a0b08aca90fdf494df1d92e15a552d2a52a3b02538c7a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f54042d6d8e987a2001e8f8b69e12f7b5e1be6322534bf71acae8f44c1d295
+oid sha256:ee11215041eb0186976ef4b18acc8c3b3085b8278e5c482e739c8198da6b7b9a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ae2baae6f9dfd7ca89f4f0f5818402f18a3e15e4581cd68734c6a76f2a7030
+oid sha256:a9244e8a4fedebd96fe9477d928481702bf2954643113838dc31cc9779fe5ad3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e81910e79bb87f0b46a0d2aa6ab0730eb92717d10eebce124863a9bc14f71612
+oid sha256:1bfe4e613c5d63b9b8661f26b2521341654055e778c8bc3f3f8cced7a4c2ef7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.533333333333333,
+  "epoch": 2.5666666666666664,
   "eval_steps": 500,
-  "global_step": 38000,
+  "global_step": 38500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2683,6 +2683,41 @@
       "learning_rate": 3.117333333333333e-06,
       "loss": 0.0477,
       "step": 38000
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.23089808225631714,
+      "learning_rate": 3.0728888888888893e-06,
+      "loss": 0.0544,
+      "step": 38100
+    },
+    {
+      "epoch": 2.546666666666667,
+      "grad_norm": 0.2545056939125061,
+      "learning_rate": 3.028444444444445e-06,
+      "loss": 0.049,
+      "step": 38200
+    },
+    {
+      "epoch": 2.5533333333333332,
+      "grad_norm": 0.2878418564796448,
+      "learning_rate": 2.984e-06,
+      "loss": 0.0506,
+      "step": 38300
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.2358868569135666,
+      "learning_rate": 2.9395555555555562e-06,
+      "loss": 0.0539,
+      "step": 38400
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.20847082138061523,
+      "learning_rate": 2.8951111111111114e-06,
+      "loss": 0.0549,
+      "step": 38500
     }
   ],
   "logging_steps": 100,
@@ -2702,7 +2737,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.256159936512e+16,
+  "total_flos": 9.377951514624e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null