Training in progress, step 13400, checkpoint

last-checkpoint/README.md

@@ -1187,6 +1187,8 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
+<details><summary>Click to expand</summary>
+
 | Epoch  | Step  | Training Loss |
 |:------:|:-----:|:-------------:|
 | 0.1458 | 8250  | 0.4688        |
@@ -1289,7 +1291,12 @@ You can finetune this model on your own dataset.
 | 0.2315 | 13100 | 0.4359        |
 | 0.2324 | 13150 | 0.3702        |
 | 0.2333 | 13200 | 0.5026        |
+| 0.2341 | 13250 | 0.5201        |
+| 0.2350 | 13300 | 0.3857        |
+| 0.2359 | 13350 | 0.3555        |
+| 0.2368 | 13400 | 0.381         |
 
+</details>
 
 ### Framework Versions
 - Python: 3.11.13

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0408532633e3d53818583ff9ef02c9be81d3ffdd069f1e604b4cdcf7a79bbd08
+oid sha256:f1ff219d2dc182bff9938951ac2d922c87f8b3382fe905eda8bb33e8c98eb346
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0884b763c5d2ec8f0b94fd605e20d3981be5785da135173f386b90a4f72ddc
+oid sha256:cbe0f24feef012ade435d0955f499b908ca4147d4a231048c8182b66d61b6f43
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff3c556549471e3b0bd6d9a3f96647cfb8a7aa9ac95f0e83191eb61af4e6bc0
+oid sha256:8c735c57cb6abf0ceb0d281a7f9e69dc9a61b723c825d122108ee089e4f92d40
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e926fae13271b40ac8f9ad92492b339eb4958bd5b878164fc6bd3383e8e0f9
+oid sha256:578b0f8cd0a36e27a4c0005bc9769962acef123517226f60d74acf957afcc72c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c897b83c9872ac7b716f5b64194b036c139fb3350016b3588f5f49c22a743418
+oid sha256:c54be013f521e475446bbdac4929f2f53d5e8b1200009f671ab53144a213230f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23325263734516088,
+  "epoch": 0.23678676821402697,
   "eval_steps": 500,
-  "global_step": 13200,
+  "global_step": 13400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1856,6 +1856,34 @@
       "learning_rate": 4.260077359564902e-05,
       "loss": 0.5026,
       "step": 13200
+    },
+    {
+      "epoch": 0.2341361700623774,
+      "grad_norm": 1.818076252937317,
+      "learning_rate": 4.2551687577310476e-05,
+      "loss": 0.5201,
+      "step": 13250
+    },
+    {
+      "epoch": 0.23501970277959394,
+      "grad_norm": 1.9688682556152344,
+      "learning_rate": 4.250260155897194e-05,
+      "loss": 0.3857,
+      "step": 13300
+    },
+    {
+      "epoch": 0.23590323549681044,
+      "grad_norm": 2.4908297061920166,
+      "learning_rate": 4.245351554063341e-05,
+      "loss": 0.3555,
+      "step": 13350
+    },
+    {
+      "epoch": 0.23678676821402697,
+      "grad_norm": 1.9015276432037354,
+      "learning_rate": 4.240442952229487e-05,
+      "loss": 0.381,
+      "step": 13400
     }
   ],
   "logging_steps": 50,