Training in progress, step 54400, checkpoint

last-checkpoint/README.md

@@ -1241,6 +1241,10 @@ You can finetune this model on your own dataset.
 | 0.9560 | 54100 | 0.3496        |
 | 0.9569 | 54150 | 0.2609        |
 | 0.9577 | 54200 | 0.3942        |
+| 0.9586 | 54250 | 0.3794        |
+| 0.9595 | 54300 | 0.2834        |
+| 0.9604 | 54350 | 0.3271        |
+| 0.9613 | 54400 | 0.3048        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c626c07a484cf440299aeab5250215215dc9a9504ba76a2c4d8cbb2ee9f703
+oid sha256:5fcfe428b137d6be6e57435ee624e959e084b7aee0c0d6305bb7c44169a76f60
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a1ca22d51c4852d7b597cdc6df536f10b0a83016c09217dd4a746f81603dfe
+oid sha256:741ae581a8dbe07cedeb95e8dcf3b75fa2e45d451017ebafac3dd8de4a759fd3
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f12eb5ebd31ffd5667160725a966706229b611b4915c7e9e0942936f7af1fe3f
+oid sha256:d18b9a5d8e4821cc664cde79b567aa4a381dd9a2d469a4b24834ee49788c1be1
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc3972897ec297e0f8185ac88e544940af5d6dbb43a2cbce3b08ddf982f52c7
+oid sha256:a37f9bfdc7ecebb937aa8d7e396f6a300da6da1986d237a8a3a3f1a8fc4e0d2b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c74d3b4e96c259643bb77262d75e1f23a0f31a3e975d23f8db0d5e5def888ead
+oid sha256:c578b2def8a7ed655790145b2a44449f69c54bd690e5b820438921a87509936b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9577494654627061,
+  "epoch": 0.9612835963315721,
   "eval_steps": 500,
-  "global_step": 54200,
+  "global_step": 54400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7596,6 +7596,34 @@
       "learning_rate": 2.3688912450177693e-06,
       "loss": 0.3942,
       "step": 54200
+    },
+    {
+      "epoch": 0.9586329981799226,
+      "grad_norm": 1.4870383739471436,
+      "learning_rate": 2.319805226679233e-06,
+      "loss": 0.3794,
+      "step": 54250
+    },
+    {
+      "epoch": 0.9595165308971392,
+      "grad_norm": 3.1990461349487305,
+      "learning_rate": 2.2707192083406965e-06,
+      "loss": 0.2834,
+      "step": 54300
+    },
+    {
+      "epoch": 0.9604000636143556,
+      "grad_norm": 1.178895115852356,
+      "learning_rate": 2.22163319000216e-06,
+      "loss": 0.3271,
+      "step": 54350
+    },
+    {
+      "epoch": 0.9612835963315721,
+      "grad_norm": 1.724674105644226,
+      "learning_rate": 2.1725471716636233e-06,
+      "loss": 0.3048,
+      "step": 54400
     }
   ],
   "logging_steps": 50,