Training in progress, step 54600, checkpoint

last-checkpoint/README.md

@@ -1245,6 +1245,10 @@ You can finetune this model on your own dataset.
 | 0.9595 | 54300 | 0.2834        |
 | 0.9604 | 54350 | 0.3271        |
 | 0.9613 | 54400 | 0.3048        |
+| 0.9622 | 54450 | 0.2813        |
+| 0.9631 | 54500 | 0.3229        |
+| 0.9639 | 54550 | 0.3064        |
+| 0.9648 | 54600 | 0.2925        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fcfe428b137d6be6e57435ee624e959e084b7aee0c0d6305bb7c44169a76f60
+oid sha256:6908b7749db5d0a826221cc7ecf07127dce59b7cc3e1282b238fab4edc8c06dc
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741ae581a8dbe07cedeb95e8dcf3b75fa2e45d451017ebafac3dd8de4a759fd3
+oid sha256:4f62d74de1aa89c4bdb621c1ad70670a4bf5390f8a562eceb290549e4b451ee2
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18b9a5d8e4821cc664cde79b567aa4a381dd9a2d469a4b24834ee49788c1be1
+oid sha256:06c5edde7f9f695c0f4e2228698ef25b87e27f53ab10a510ae3e7d0707680eae
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37f9bfdc7ecebb937aa8d7e396f6a300da6da1986d237a8a3a3f1a8fc4e0d2b
+oid sha256:722f444d07f10344822682b1f6fd20e81bcbd5d550a56fbe82dc92a7f96b7a4c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c578b2def8a7ed655790145b2a44449f69c54bd690e5b820438921a87509936b
+oid sha256:2266beea22f5d851f4cb4c5de2987869a11c52788a165a553f5636a0c72bb073
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9612835963315721,
+  "epoch": 0.9648177272004382,
   "eval_steps": 500,
-  "global_step": 54400,
+  "global_step": 54600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7624,6 +7624,34 @@
       "learning_rate": 2.1725471716636233e-06,
       "loss": 0.3048,
       "step": 54400
+    },
+    {
+      "epoch": 0.9621671290487886,
+      "grad_norm": 1.5154780149459839,
+      "learning_rate": 2.1234611533250867e-06,
+      "loss": 0.2813,
+      "step": 54450
+    },
+    {
+      "epoch": 0.9630506617660052,
+      "grad_norm": 1.3216954469680786,
+      "learning_rate": 2.0743751349865505e-06,
+      "loss": 0.3229,
+      "step": 54500
+    },
+    {
+      "epoch": 0.9639341944832217,
+      "grad_norm": 1.5333393812179565,
+      "learning_rate": 2.0252891166480143e-06,
+      "loss": 0.3064,
+      "step": 54550
+    },
+    {
+      "epoch": 0.9648177272004382,
+      "grad_norm": 1.3715639114379883,
+      "learning_rate": 1.9762030983094777e-06,
+      "loss": 0.2925,
+      "step": 54600
     }
   ],
   "logging_steps": 50,