Training in progress, step 27600, checkpoint

last-checkpoint/README.md

@@ -1209,6 +1209,10 @@ You can finetune this model on your own dataset.
 | 0.4824 | 27300 | 0.3246        |
 | 0.4833 | 27350 | 0.3131        |
 | 0.4842 | 27400 | 0.3078        |
+| 0.4851 | 27450 | 0.419         |
+| 0.4859 | 27500 | 0.3959        |
+| 0.4868 | 27550 | 0.3754        |
+| 0.4877 | 27600 | 0.3163        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42bafc26f64fc942eebe9b36d05cb9ebd690bc7e84350aba5ef5927bebd23aa
+oid sha256:7664a0a0f5ecfa598f2701a1ff37b213f978409532fb7f103898692f18c2a725
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86493a89e1b924fce58823b6948f096f29423c5ce2b1e2b2de815c28e7f95699
+oid sha256:c9a099107f68059125238e954d06fc6e590362c99b51020b9fe7fdd85f6a409e
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ffba3c8137c0af09582c28fee3245b77ce6875ddb2ff1a79f1003af6257b2b
+oid sha256:4e5363905a5180ae7b6dc66d9d24e9725568295ce2578c5fa9423e53d3f4ca3e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79db97c4b1cd4a4d432cc88a5b1b07dc74a6838264e86b10e57ab5d0be29f45
+oid sha256:01018da1a415cc4a2591785629b35e825cfe5ca85d564c2b7250cf57ca5ee003
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10c98a9a1e72b7cb62494c74d5b84c2a61b0c8fb7089e16aa24c2bd64d181a5f
+oid sha256:52a4e22174e8f57aba7a9808391b59167576034c6b53740dc89da4532411a156
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4841759290346522,
+  "epoch": 0.48771005990351823,
   "eval_steps": 500,
-  "global_step": 27400,
+  "global_step": 27600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3844,6 +3844,34 @@
       "learning_rate": 2.8667216430072057e-05,
       "loss": 0.3078,
       "step": 27400
+    },
+    {
+      "epoch": 0.48505946175186865,
+      "grad_norm": 1.3667497634887695,
+      "learning_rate": 2.8618130411733522e-05,
+      "loss": 0.419,
+      "step": 27450
+    },
+    {
+      "epoch": 0.4859429944690852,
+      "grad_norm": 4.66032075881958,
+      "learning_rate": 2.856904439339499e-05,
+      "loss": 0.3959,
+      "step": 27500
+    },
+    {
+      "epoch": 0.4868265271863017,
+      "grad_norm": 1.530393362045288,
+      "learning_rate": 2.8519958375056448e-05,
+      "loss": 0.3754,
+      "step": 27550
+    },
+    {
+      "epoch": 0.48771005990351823,
+      "grad_norm": 0.9399372935295105,
+      "learning_rate": 2.8470872356717916e-05,
+      "loss": 0.3163,
+      "step": 27600
     }
   ],
   "logging_steps": 50,