Training in progress, step 49400, checkpoint

last-checkpoint/README.md

@@ -1277,6 +1277,10 @@ You can finetune this model on your own dataset.
 | 0.8676 | 49100 | 0.3881        |
 | 0.8685 | 49150 | 0.253         |
 | 0.8694 | 49200 | 0.2827        |
+| 0.8703 | 49250 | 0.266         |
+| 0.8712 | 49300 | 0.3008        |
+| 0.8720 | 49350 | 0.3406        |
+| 0.8729 | 49400 | 0.3348        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db270bdf7d87010d77739736698e8ae2458178b320b75a98ff547807297b32cf
+oid sha256:3d54875bf531798288ddb4b3fbae3f4ae380603d3b22e5d05230773e3c542f66
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cdff63ae89dbc12a252704b70d4f4e647e5f14e3b07054703b4d441104730c5
+oid sha256:cf9cbc9f060e9473758fc47c31fa40ee4cde249f6a49d58103beecc7d51b4a81
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9fcb3d1d73275e0a2875dc17b667a53e5fe939e399224550e0ccf13df80b1e
+oid sha256:51c3b32231fb132bb00c65088bba338cce412cdb74ffd139a1f27a4b9e6c9314
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3068685ac3b9a7af5938020cc76babca30a1c59648f52293d5fd49a933b85d96
+oid sha256:f8d9e833107ed9942fa0d2735bf0fb4ceb0909143f01ecba6b48822116d17b49
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ba2b0f751d8d7f4bc3cb94f7968aeae57ec5b067c86272a37019de0cca79bf
+oid sha256:be95a1e2a9d21081dedb60183caea1d3c628d9f653733abb462690fc704b6522
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8693961937410543,
+  "epoch": 0.8729303246099203,
   "eval_steps": 500,
-  "global_step": 49200,
+  "global_step": 49400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6896,6 +6896,34 @@
       "learning_rate": 7.2755296381378734e-06,
       "loss": 0.2827,
       "step": 49200
+    },
+    {
+      "epoch": 0.8702797264582708,
+      "grad_norm": 1.333967924118042,
+      "learning_rate": 7.2264436197993364e-06,
+      "loss": 0.266,
+      "step": 49250
+    },
+    {
+      "epoch": 0.8711632591754873,
+      "grad_norm": 1.3817411661148071,
+      "learning_rate": 7.1773576014608e-06,
+      "loss": 0.3008,
+      "step": 49300
+    },
+    {
+      "epoch": 0.8720467918927037,
+      "grad_norm": 1.269362211227417,
+      "learning_rate": 7.128271583122263e-06,
+      "loss": 0.3406,
+      "step": 49350
+    },
+    {
+      "epoch": 0.8729303246099203,
+      "grad_norm": 1.5153824090957642,
+      "learning_rate": 7.079185564783727e-06,
+      "loss": 0.3348,
+      "step": 49400
     }
   ],
   "logging_steps": 50,