Training in progress, step 41800, checkpoint

last-checkpoint/README.md

@@ -1351,6 +1351,10 @@ You can finetune this model on your own dataset.
 | 0.7333 | 41500 | 0.3016        |
 | 0.7342 | 41550 | 0.3232        |
 | 0.7351 | 41600 | 0.2577        |
+| 0.7360 | 41650 | 0.2928        |
+| 0.7369 | 41700 | 0.2814        |
+| 0.7377 | 41750 | 0.2962        |
+| 0.7386 | 41800 | 0.2756        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5968fa9233e27ceab0b50d025526b14878df9c3a5cc0dd8ab8e3bfb4e8731159
+oid sha256:abfcfd3f457cbe51abbd61ecc95245359c5208d8775c26e09de127916a470d92
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9b287a89c14a672aa169e1144107274fac0f234f450dc15728e411970cfec4
+oid sha256:fb67670e66bb3f0f4adc4b392b33cd6c165031c08ca7ad68859e8241c86a12f3
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c7015785925a4c92109508d00189934d2658c038f9a9b3126f34a88d70d109
+oid sha256:e3ac5b3de4f8e2849792c1b106634d8b16fc3919a657dbd8cbb3d224121e1301
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd530e72b22c1ce77a70b73b0e2553d90cdc69cb660d5df5b7ea28fe660cd767
+oid sha256:8814987cfbe269e51b2a3098b07850feb46aab6ef117c55c4f2b6aaf9ac85aa0
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36751f2c6aca47874fa4d1553b1d00dffae813bb24cca7967068d98d45a147e3
+oid sha256:bcfbb3dbbb2ba7d17dd131f713778ca8f3b0e144d05efa9885ea8327cd9b4a6f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7350992207241435,
+  "epoch": 0.7386333515930095,
   "eval_steps": 500,
-  "global_step": 41600,
+  "global_step": 41800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5832,6 +5832,34 @@
       "learning_rate": 1.4732677544128332e-05,
       "loss": 0.2577,
       "step": 41600
+    },
+    {
+      "epoch": 0.7359827534413599,
+      "grad_norm": 1.0362133979797363,
+      "learning_rate": 1.4683591525789795e-05,
+      "loss": 0.2928,
+      "step": 41650
+    },
+    {
+      "epoch": 0.7368662861585764,
+      "grad_norm": 2.07706618309021,
+      "learning_rate": 1.4634505507451258e-05,
+      "loss": 0.2814,
+      "step": 41700
+    },
+    {
+      "epoch": 0.7377498188757929,
+      "grad_norm": 1.6817320585250854,
+      "learning_rate": 1.4585419489112722e-05,
+      "loss": 0.2962,
+      "step": 41750
+    },
+    {
+      "epoch": 0.7386333515930095,
+      "grad_norm": 2.021404981613159,
+      "learning_rate": 1.4536333470774185e-05,
+      "loss": 0.2756,
+      "step": 41800
     }
   ],
   "logging_steps": 50,