Training in progress, step 37400, checkpoint

last-checkpoint/README.md

@@ -1261,6 +1261,10 @@ You can finetune this model on your own dataset.
 | 0.6556 | 37100 | 0.3814        |
 | 0.6565 | 37150 | 0.4174        |
 | 0.6573 | 37200 | 0.3473        |
+| 0.6582 | 37250 | 0.3598        |
+| 0.6591 | 37300 | 0.2822        |
+| 0.6600 | 37350 | 0.2538        |
+| 0.6609 | 37400 | 0.2212        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078012c454ea4b152c3db74341399805978d346a3159daf28a1763d42680059c
+oid sha256:682fa9590e06a4b4fccae7f5f773e5cc53952c5e99d2335a76b83158b65098ed
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f250b4f70e94e35dd162d4656e5953ae96031e8d6e24791ea917a2422dac3a
+oid sha256:9245c8c24824eb122166f727d92f67c72576954b6b177342efb7c87cca99916e
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2134ce16464c1d7c26a8d74b225ed50e24c2ef21aefdbfa44036477c7f93a57
+oid sha256:4055cc979b2b5391466d56f1b911260413ca5d1e7980d72b0ab4b419cbf9b1f2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af84d11cf9a350709c490c3f7b9bde1e09340d958fac411ecff8f1d22ce1e52
+oid sha256:88bd0768fb513693c45a5dd657bdd8c5632ab92debcf304b18dc0e31cdbf92a9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ffdf18d69e9e8219490bafd2eb8c151c526102e648991721d9f0d64d7104e24
+oid sha256:e0f778ab4b27197de7dc711e3e33f3210ad38a94a9b2fa894dde1075de7a2d68
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6573483416090898,
+  "epoch": 0.6608824724779558,
   "eval_steps": 500,
-  "global_step": 37200,
+  "global_step": 37400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5216,6 +5216,34 @@
       "learning_rate": 1.9050283717185998e-05,
       "loss": 0.3473,
       "step": 37200
+    },
+    {
+      "epoch": 0.6582318743263063,
+      "grad_norm": 1.6960564851760864,
+      "learning_rate": 1.9001197698847463e-05,
+      "loss": 0.3598,
+      "step": 37250
+    },
+    {
+      "epoch": 0.6591154070435228,
+      "grad_norm": 1.8127328157424927,
+      "learning_rate": 1.8952111680508924e-05,
+      "loss": 0.2822,
+      "step": 37300
+    },
+    {
+      "epoch": 0.6599989397607393,
+      "grad_norm": 1.7553006410598755,
+      "learning_rate": 1.890302566217039e-05,
+      "loss": 0.2538,
+      "step": 37350
+    },
+    {
+      "epoch": 0.6608824724779558,
+      "grad_norm": 1.111005187034607,
+      "learning_rate": 1.8853939643831853e-05,
+      "loss": 0.2212,
+      "step": 37400
     }
   ],
   "logging_steps": 50,