Training in progress, step 39600, checkpoint

last-checkpoint/README.md

@@ -1307,6 +1307,10 @@ You can finetune this model on your own dataset.
 | 0.6945 | 39300 | 0.3039        |
 | 0.6953 | 39350 | 0.2616        |
 | 0.6962 | 39400 | 0.2932        |
+| 0.6971 | 39450 | 0.3707        |
+| 0.6980 | 39500 | 0.2728        |
+| 0.6989 | 39550 | 0.2482        |
+| 0.6998 | 39600 | 0.3475        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94767fd5b6dc20de49ba334fd663d49bbab52439b211b34b6edd17e30405b86c
+oid sha256:642557ebf163ec87a2c4b2e6bcd49164daf736dd04b223bf43c296aa2ccd0691
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2146c07d6c292a2316614d7a7b9fe3a693a9e0eea9764160ec4f5efec7166df8
+oid sha256:68fc796162e803cf8996cea52a774af09ba5e5580bd153dfb078c7440eb4c453
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf8f818b4d7a0be92e772ae0a75f67d80a9b767e05b6e9aa8f81d57f578b5ec
+oid sha256:64e9f5adbd47cc46da9040df21f1d7ee84a7337e4df1a6edd24bdcba55b2b18f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94fbce33b74f960529cb34bc94a882a154a6272486e6b5ab9ab677e9a88bdc6d
+oid sha256:e5969956edb13fe3030fe262e095ce3767ee21141a5bf0b22d9012217adf4404
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7bfee7ee542a2c30ee052be1eff9c687ace2bd0997831ad2274df374589ca0
+oid sha256:7a02d77869643a47791f7c775e6b5711819ede3a850a6716616e73ea72431d66
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6962237811666167,
+  "epoch": 0.6997579120354827,
   "eval_steps": 500,
-  "global_step": 39400,
+  "global_step": 39600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5524,6 +5524,34 @@
       "learning_rate": 1.6891480630657162e-05,
       "loss": 0.2932,
       "step": 39400
+    },
+    {
+      "epoch": 0.6971073138838331,
+      "grad_norm": 1.3213509321212769,
+      "learning_rate": 1.6842394612318627e-05,
+      "loss": 0.3707,
+      "step": 39450
+    },
+    {
+      "epoch": 0.6979908466010496,
+      "grad_norm": 1.9010616540908813,
+      "learning_rate": 1.679330859398009e-05,
+      "loss": 0.2728,
+      "step": 39500
+    },
+    {
+      "epoch": 0.6988743793182661,
+      "grad_norm": 1.143967866897583,
+      "learning_rate": 1.6744222575641556e-05,
+      "loss": 0.2482,
+      "step": 39550
+    },
+    {
+      "epoch": 0.6997579120354827,
+      "grad_norm": 1.108268141746521,
+      "learning_rate": 1.6695136557303018e-05,
+      "loss": 0.3475,
+      "step": 39600
     }
   ],
   "logging_steps": 50,