Training in progress, step 51000, checkpoint

last-checkpoint/README.md

@@ -1311,6 +1311,10 @@ You can finetune this model on your own dataset.
 | 0.8959 | 50700 | 0.2947        |
 | 0.8968 | 50750 | 0.3013        |
 | 0.8977 | 50800 | 0.3845        |
+| 0.8986 | 50850 | 0.2882        |
+| 0.8994 | 50900 | 0.3639        |
+| 0.9003 | 50950 | 0.2332        |
+| 0.9012 | 51000 | 0.3363        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735447a9bf44cea3982a63ea1f966e08b7318fb0e661723166d288f02b87e519
+oid sha256:8e5b296e1f58fde06ca25a671f7290066af40d31d74f593dd71beb56e81f618e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2850e2599deef45e89d0f9a762b74aca5edd8c76810f98fd68acb5fea8d7226
+oid sha256:64cec233f06e1ea5350dc36447e7fd4afa810289f7a83dc18968cd19ae207a12
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c5b25f41326cbbfda1e3a08018f1c0a2d702a29def2a1a126e092c108f1e2b
+oid sha256:c2b900393780cdd3cbb99d501f19a790b00c5891d77d31ffa5ebe767f48b02bb
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eecf2b6d210d44959e71df0344547cefe9b13a61cd7bf96084fa2fabddd2a6b
+oid sha256:30c99faa590c236be1e60450ac31ef6bbc0d8a5408817f47526e33c981695098
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3068e69bbcee94c299b9e89630d72a89daebc924a613171ca109523fc3200153
+oid sha256:2640c4dcf9a6fa010a98a2ceb775abaf0e70fd53baf808dd65285ab30eadea3f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8976692406919828,
+  "epoch": 0.901203371560849,
   "eval_steps": 500,
-  "global_step": 50800,
+  "global_step": 51000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7120,6 +7120,34 @@
       "learning_rate": 5.704777051304706e-06,
       "loss": 0.3845,
       "step": 50800
+    },
+    {
+      "epoch": 0.8985527734091994,
+      "grad_norm": 1.9302955865859985,
+      "learning_rate": 5.65569103296617e-06,
+      "loss": 0.2882,
+      "step": 50850
+    },
+    {
+      "epoch": 0.8994363061264159,
+      "grad_norm": 2.9837305545806885,
+      "learning_rate": 5.606605014627634e-06,
+      "loss": 0.3639,
+      "step": 50900
+    },
+    {
+      "epoch": 0.9003198388436324,
+      "grad_norm": 1.3305821418762207,
+      "learning_rate": 5.557518996289098e-06,
+      "loss": 0.2332,
+      "step": 50950
+    },
+    {
+      "epoch": 0.901203371560849,
+      "grad_norm": 1.2136187553405762,
+      "learning_rate": 5.508432977950561e-06,
+      "loss": 0.3363,
+      "step": 51000
     }
   ],
   "logging_steps": 50,