Training in progress, step 8800, checkpoint

last-checkpoint/README.md

@@ -1197,6 +1197,10 @@ You can finetune this model on your own dataset.
 | 0.1502 | 8500 | 0.4203        |
 | 0.1511 | 8550 | 0.414         |
 | 0.1520 | 8600 | 0.3436        |
+| 0.1529 | 8650 | 0.436         |
+| 0.1537 | 8700 | 0.3761        |
+| 0.1546 | 8750 | 0.5579        |
+| 0.1555 | 8800 | 0.441         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03eb7a5af20bd02ca3c82b2b9c70071b68c323ac87a7799ea87cd5139a94eb91
+oid sha256:48362ba7fcb9b7f2c1aa7030a50c6258f1f4d6cc4f1665e7ca632872744db5c0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40262b6becfc7b5455f773e7a9a3bb594892eb51a5604b32e91c90609a89bdfb
+oid sha256:75a1f68b3f77c2bf8fd6e4f0bdee7b8ce97a773c56cdc7093cbfde49c00998f8
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f5a47fc1fb0afabfab2902b2aa5af7ab84c4d2097ab2d93b83ccc74c03acb1
+oid sha256:14cd2e3712404ebb968f80623888d77e60a6a55be515062adfbd0e098660e63a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b161abd57fc77c436995db62a6c89b28c6220f59213ab301dd9a979ea4c14232
+oid sha256:7d6c0ca588079b6a2e8be7c5b7bc6af97572af78d73d1dce8d6f30fcc361b6a3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c145ff6cd9415e52757f69b1d04fadde604f73651764ac12eda7fa02fc8ae0
+oid sha256:89db5df6d87e4cc0368652d8350a2c32d46bae130899047ae58e000eec6fa2a0
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1519676273612412,
+  "epoch": 0.15550175823010726,
   "eval_steps": 500,
-  "global_step": 8600,
+  "global_step": 8800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1212,6 +1212,34 @@
       "learning_rate": 4.711472384206083e-05,
       "loss": 0.3436,
       "step": 8600
+    },
+    {
+      "epoch": 0.1528511600784577,
+      "grad_norm": 2.2018544673919678,
+      "learning_rate": 4.706563782372229e-05,
+      "loss": 0.436,
+      "step": 8650
+    },
+    {
+      "epoch": 0.15373469279567423,
+      "grad_norm": 1.5418767929077148,
+      "learning_rate": 4.701655180538376e-05,
+      "loss": 0.3761,
+      "step": 8700
+    },
+    {
+      "epoch": 0.15461822551289076,
+      "grad_norm": 4.974616050720215,
+      "learning_rate": 4.6967465787045225e-05,
+      "loss": 0.5579,
+      "step": 8750
+    },
+    {
+      "epoch": 0.15550175823010726,
+      "grad_norm": 1.8653486967086792,
+      "learning_rate": 4.691837976870668e-05,
+      "loss": 0.441,
+      "step": 8800
     }
   ],
   "logging_steps": 50,