Training in progress, step 320, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7b638956b5aefb96216cebb0cc4e2f5ca1f4b0731b8919df07c83dde33eab2
+oid sha256:c2e4c22cf9e06580af30dce4f279974ede0ee3634a0dd139bd26cb4e25b25ed7
 size 936503576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43017fbec9c8da66ae23541f07595a7ae4286d452825f32083f5e398be89f0ed
+oid sha256:7344bdd1e274ca01246f02556985f7a2cd03b4f3e5340ec3a06f3c587c4caa39
 size 936544523

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:949550c402a32533c4218565004de685bebcce6068fb43f8dd1d8fe10cec0d5b
+oid sha256:d97c0d3c8cfa82dd1ce5510efad605477e606178221dbf394aa018e5e13a0c32
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001378087081767241,
+  "epoch": 0.0014225415037597328,
   "eval_steps": 500,
-  "global_step": 310,
+  "global_step": 320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2178,6 +2178,76 @@
       "learning_rate": 1.9999998545088225e-05,
       "loss": 4.3453,
       "step": 310
+    },
+    {
+      "epoch": 0.0013825325239664903,
+      "grad_norm": 13.375,
+      "learning_rate": 1.999999853565608e-05,
+      "loss": 4.3769,
+      "step": 311
+    },
+    {
+      "epoch": 0.0013869779661657394,
+      "grad_norm": 12.75,
+      "learning_rate": 1.999999852619346e-05,
+      "loss": 4.2999,
+      "step": 312
+    },
+    {
+      "epoch": 0.0013914234083649887,
+      "grad_norm": 13.1875,
+      "learning_rate": 1.9999998516700373e-05,
+      "loss": 4.4593,
+      "step": 313
+    },
+    {
+      "epoch": 0.0013958688505642377,
+      "grad_norm": 12.75,
+      "learning_rate": 1.9999998507176803e-05,
+      "loss": 4.4465,
+      "step": 314
+    },
+    {
+      "epoch": 0.001400314292763487,
+      "grad_norm": 12.5625,
+      "learning_rate": 1.9999998497622755e-05,
+      "loss": 4.301,
+      "step": 315
+    },
+    {
+      "epoch": 0.001404759734962736,
+      "grad_norm": 11.625,
+      "learning_rate": 1.999999848803824e-05,
+      "loss": 4.7077,
+      "step": 316
+    },
+    {
+      "epoch": 0.0014092051771619853,
+      "grad_norm": 10.75,
+      "learning_rate": 1.9999998478423243e-05,
+      "loss": 4.3979,
+      "step": 317
+    },
+    {
+      "epoch": 0.0014136506193612344,
+      "grad_norm": 8.1875,
+      "learning_rate": 1.9999998468777773e-05,
+      "loss": 4.4527,
+      "step": 318
+    },
+    {
+      "epoch": 0.0014180960615604835,
+      "grad_norm": 12.5,
+      "learning_rate": 1.9999998459101828e-05,
+      "loss": 4.3529,
+      "step": 319
+    },
+    {
+      "epoch": 0.0014225415037597328,
+      "grad_norm": 13.6875,
+      "learning_rate": 1.9999998449395407e-05,
+      "loss": 4.2385,
+      "step": 320
     }
   ],
   "logging_steps": 1,
@@ -2197,7 +2267,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.22720788414464e+16,
+  "total_flos": 1.26679523524608e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null