Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9fe2f48e8378500e219fdf03eba20a43b9479ae9e51d99d2834207e227a5afa
+oid sha256:c416859fe44e8b6d5cb48a9782e6f50fd51541dcab765af23144123ba2fe7971
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be034ae5511758d5bc34a1be0302bdadf4332dce4838198ff42767a450dc0e21
+oid sha256:61c98bad3ea164698c925b2c088cccf6c87624823b19a3514843aafecdd26735
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad48a0d534797ba9c753d5040c6945a0f046d49c6d83c7b94ef7caaa9b29d97e
+oid sha256:2128f689a6302c47cffe9b18c691d685bfb7c7c4df1c1367d77ca12e87395223
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6301946344029457,
+  "epoch": 5.260389268805891,
   "eval_steps": 20000,
-  "global_step": 20000,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,34 @@
       "learning_rate": 5e-05,
       "loss": 0.0022,
       "step": 20000
+    },
+    {
+      "epoch": 3.2877432930036825,
+      "grad_norm": 0.03226898983120918,
+      "learning_rate": 5e-05,
+      "loss": 0.0017,
+      "step": 25000
+    },
+    {
+      "epoch": 3.9452919516044185,
+      "grad_norm": 0.027553141117095947,
+      "learning_rate": 5e-05,
+      "loss": 0.0014,
+      "step": 30000
+    },
+    {
+      "epoch": 4.602840610205155,
+      "grad_norm": 0.033046554774045944,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 35000
+    },
+    {
+      "epoch": 5.260389268805891,
+      "grad_norm": 0.05404861643910408,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 40000
     }
   ],
   "logging_steps": 5000,
@@ -54,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7387426410083302e+17,
+  "total_flos": 3.477887493977829e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null