Training in progress, step 39000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61083c956d931fcb4b0a0b08aca90fdf494df1d92e15a552d2a52a3b02538c7a
+oid sha256:d8cd71b89eb4cf5b54368e95fa13ee6cc3864c3091e759091438dd601d6f1af7
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee11215041eb0186976ef4b18acc8c3b3085b8278e5c482e739c8198da6b7b9a
+oid sha256:dc0dd7a1f2c9ad84ebf73220aa56cda18faf115b1e79f8dbee1b26db6cddaa7d
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9244e8a4fedebd96fe9477d928481702bf2954643113838dc31cc9779fe5ad3
+oid sha256:823ea6f73dcec531968a187071c6ecff33e9bb6c6d030f15a43dbc4f25e7c39e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bfe4e613c5d63b9b8661f26b2521341654055e778c8bc3f3f8cced7a4c2ef7b
+oid sha256:90e54113eca63b2259f253dad8dc263308f86084513f881434f4da417da62d75
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5666666666666664,
+  "epoch": 2.6,
   "eval_steps": 500,
-  "global_step": 38500,
+  "global_step": 39000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2718,6 +2718,41 @@
       "learning_rate": 2.8951111111111114e-06,
       "loss": 0.0549,
       "step": 38500
+    },
+    {
+      "epoch": 2.5733333333333333,
+      "grad_norm": 0.16107220947742462,
+      "learning_rate": 2.850666666666667e-06,
+      "loss": 0.0549,
+      "step": 38600
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.14319832623004913,
+      "learning_rate": 2.8062222222222223e-06,
+      "loss": 0.0508,
+      "step": 38700
+    },
+    {
+      "epoch": 2.586666666666667,
+      "grad_norm": 0.13144062459468842,
+      "learning_rate": 2.7617777777777784e-06,
+      "loss": 0.0491,
+      "step": 38800
+    },
+    {
+      "epoch": 2.5933333333333333,
+      "grad_norm": 0.202744722366333,
+      "learning_rate": 2.7173333333333336e-06,
+      "loss": 0.0531,
+      "step": 38900
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.1617712527513504,
+      "learning_rate": 2.6728888888888893e-06,
+      "loss": 0.0516,
+      "step": 39000
     }
   ],
   "logging_steps": 100,
@@ -2737,7 +2772,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.377951514624e+16,
+  "total_flos": 9.499743092736e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null