Training in progress, step 42000, checkpoint

last-checkpoint/README.md

@@ -1355,6 +1355,10 @@ You can finetune this model on your own dataset.
 | 0.7369 | 41700 | 0.2814        |
 | 0.7377 | 41750 | 0.2962        |
 | 0.7386 | 41800 | 0.2756        |
+| 0.7395 | 41850 | 0.3287        |
+| 0.7404 | 41900 | 0.34          |
+| 0.7413 | 41950 | 0.3402        |
+| 0.7422 | 42000 | 0.2404        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfcfd3f457cbe51abbd61ecc95245359c5208d8775c26e09de127916a470d92
+oid sha256:e57b3e2b58d734f4c35cbc52b8711045e136c227d6cc5e1dcddb6a3c1910ff6e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb67670e66bb3f0f4adc4b392b33cd6c165031c08ca7ad68859e8241c86a12f3
+oid sha256:81694f45179e6fe9a2996d2cdf88f73c60893feef53e707cd5693d75ccfd65f7
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ac5b3de4f8e2849792c1b106634d8b16fc3919a657dbd8cbb3d224121e1301
+oid sha256:189c7583745a64b89aee209b7060333b361b8f00c73935be83712585003d2b83
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8814987cfbe269e51b2a3098b07850feb46aab6ef117c55c4f2b6aaf9ac85aa0
+oid sha256:f9f620c9a2a7cac59f29c3864d51fa02083d5c4a45835ed46377aa71b80487d3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfbb3dbbb2ba7d17dd131f713778ca8f3b0e144d05efa9885ea8327cd9b4a6f
+oid sha256:191a5ae829d69c8ce786757578a128230a22a499f634555db1cb0373af1f974a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7386333515930095,
+  "epoch": 0.7421674824618756,
   "eval_steps": 500,
-  "global_step": 41800,
+  "global_step": 42000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5860,6 +5860,34 @@
       "learning_rate": 1.4536333470774185e-05,
       "loss": 0.2756,
       "step": 41800
+    },
+    {
+      "epoch": 0.739516884310226,
+      "grad_norm": 1.3860830068588257,
+      "learning_rate": 1.4487247452435648e-05,
+      "loss": 0.3287,
+      "step": 41850
+    },
+    {
+      "epoch": 0.7404004170274425,
+      "grad_norm": 1.266453742980957,
+      "learning_rate": 1.4438161434097111e-05,
+      "loss": 0.34,
+      "step": 41900
+    },
+    {
+      "epoch": 0.741283949744659,
+      "grad_norm": 1.5601640939712524,
+      "learning_rate": 1.4389075415758576e-05,
+      "loss": 0.3402,
+      "step": 41950
+    },
+    {
+      "epoch": 0.7421674824618756,
+      "grad_norm": 1.6014955043792725,
+      "learning_rate": 1.4339989397420039e-05,
+      "loss": 0.2404,
+      "step": 42000
     }
   ],
   "logging_steps": 50,