Training in progress, step 37200, checkpoint

last-checkpoint/README.md

@@ -1257,6 +1257,10 @@ You can finetune this model on your own dataset.
 | 0.6520 | 36900 | 0.3572        |
 | 0.6529 | 36950 | 0.3085        |
 | 0.6538 | 37000 | 0.2647        |
+| 0.6547 | 37050 | 0.2622        |
+| 0.6556 | 37100 | 0.3814        |
+| 0.6565 | 37150 | 0.4174        |
+| 0.6573 | 37200 | 0.3473        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa3e074a25abb8c340316265b8419fb45e38d5ea71e4312b6d0194cb38cc86b
+oid sha256:078012c454ea4b152c3db74341399805978d346a3159daf28a1763d42680059c
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86c17b77d1cfac3584af9a6619882b78c1f9bc7dcb85e0259432165076b9f36
+oid sha256:06f250b4f70e94e35dd162d4656e5953ae96031e8d6e24791ea917a2422dac3a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da82f98ab298f77c390cd353b9bced87815dd73e91293360907ff091eb61d4e
+oid sha256:b2134ce16464c1d7c26a8d74b225ed50e24c2ef21aefdbfa44036477c7f93a57
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952a0b2337ddfcc5838b84a78a584c51460d6072b3d324731f0a62584e450719
+oid sha256:0af84d11cf9a350709c490c3f7b9bde1e09340d958fac411ecff8f1d22ce1e52
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a249cc3fbdfe88ea20fb6dbfcb1191ec424d82ef41e7dafc1d1c85f14b5994e9
+oid sha256:2ffdf18d69e9e8219490bafd2eb8c151c526102e648991721d9f0d64d7104e24
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6538142107402237,
+  "epoch": 0.6573483416090898,
   "eval_steps": 500,
-  "global_step": 37000,
+  "global_step": 37200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5188,6 +5188,34 @@
       "learning_rate": 1.9246627790540143e-05,
       "loss": 0.2647,
       "step": 37000
+    },
+    {
+      "epoch": 0.6546977434574403,
+      "grad_norm": 1.230721354484558,
+      "learning_rate": 1.9197541772201607e-05,
+      "loss": 0.2622,
+      "step": 37050
+    },
+    {
+      "epoch": 0.6555812761746568,
+      "grad_norm": 1.6303822994232178,
+      "learning_rate": 1.9148455753863072e-05,
+      "loss": 0.3814,
+      "step": 37100
+    },
+    {
+      "epoch": 0.6564648088918733,
+      "grad_norm": 1.2327115535736084,
+      "learning_rate": 1.9099369735524533e-05,
+      "loss": 0.4174,
+      "step": 37150
+    },
+    {
+      "epoch": 0.6573483416090898,
+      "grad_norm": 1.4918360710144043,
+      "learning_rate": 1.9050283717185998e-05,
+      "loss": 0.3473,
+      "step": 37200
     }
   ],
   "logging_steps": 50,