Training in progress, step 49600, checkpoint

last-checkpoint/README.md

@@ -1281,6 +1281,10 @@ You can finetune this model on your own dataset.
 | 0.8712 | 49300 | 0.3008        |
 | 0.8720 | 49350 | 0.3406        |
 | 0.8729 | 49400 | 0.3348        |
+| 0.8738 | 49450 | 0.3021        |
+| 0.8747 | 49500 | 0.3182        |
+| 0.8756 | 49550 | 0.3063        |
+| 0.8765 | 49600 | 0.2385        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d54875bf531798288ddb4b3fbae3f4ae380603d3b22e5d05230773e3c542f66
+oid sha256:8131e17a996f8828e5a4d3b270f9fd8ff6e941e36a00908536ef7a5e8550aaba
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9cbc9f060e9473758fc47c31fa40ee4cde249f6a49d58103beecc7d51b4a81
+oid sha256:8e1ac75d8f0e3ef9befe27d47520e773ab09b8e31d1344e3def76ce5cd49eb10
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c3b32231fb132bb00c65088bba338cce412cdb74ffd139a1f27a4b9e6c9314
+oid sha256:281a95f6afaa2c9511c5ed8a9ce2381872188baca75f43c1972f2ab2f8eef316
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d9e833107ed9942fa0d2735bf0fb4ceb0909143f01ecba6b48822116d17b49
+oid sha256:8cac657ef6092bde192981138bb915fe2e134b5e72b8ef8fc2e6cf2847fb45f5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be95a1e2a9d21081dedb60183caea1d3c628d9f653733abb462690fc704b6522
+oid sha256:81093c41fdabf9a6d7f304a197f461407189d93225316dffdaf89ead0f00b3f5
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8729303246099203,
+  "epoch": 0.8764644554787864,
   "eval_steps": 500,
-  "global_step": 49400,
+  "global_step": 49600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6924,6 +6924,34 @@
       "learning_rate": 7.079185564783727e-06,
       "loss": 0.3348,
       "step": 49400
+    },
+    {
+      "epoch": 0.8738138573271368,
+      "grad_norm": 1.6337603330612183,
+      "learning_rate": 7.03009954644519e-06,
+      "loss": 0.3021,
+      "step": 49450
+    },
+    {
+      "epoch": 0.8746973900443533,
+      "grad_norm": 1.4994523525238037,
+      "learning_rate": 6.981013528106655e-06,
+      "loss": 0.3182,
+      "step": 49500
+    },
+    {
+      "epoch": 0.8755809227615698,
+      "grad_norm": 1.2485002279281616,
+      "learning_rate": 6.9319275097681185e-06,
+      "loss": 0.3063,
+      "step": 49550
+    },
+    {
+      "epoch": 0.8764644554787864,
+      "grad_norm": 1.538524866104126,
+      "learning_rate": 6.8828414914295815e-06,
+      "loss": 0.2385,
+      "step": 49600
     }
   ],
   "logging_steps": 50,