Training in progress, step 11000, checkpoint

last-checkpoint/README.md

@@ -1241,6 +1241,10 @@ You can finetune this model on your own dataset.
 | 0.1891 | 10700 | 0.3533        |
 | 0.1900 | 10750 | 0.5213        |
 | 0.1908 | 10800 | 0.4372        |
+| 0.1917 | 10850 | 0.3286        |
+| 0.1926 | 10900 | 0.4082        |
+| 0.1935 | 10950 | 0.4056        |
+| 0.1944 | 11000 | 0.4435        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f408adec52fbb09d85249b52246fc558988060284c8e9e89545510e5f53f1fe
+oid sha256:68fa837444bb1d1983506586971bf36bcb05644b535c7a58278e0f70de2e98b7
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a277a8a603891a188ecd4a7bff193d0e3832dc4f4e3f75b9504c7a244433a2
+oid sha256:22e30cc5ca132903fd2a4ed91cad71091631f1cc2f4eba3197af287eeafbaf42
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39af6a910c9139a42774120919755175edcea033ab599451e3e8ba8327efe56
+oid sha256:e22fe178097ffc288163bb2b208108bb4bcac4332048a6b0583e8f00c3efbf3d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618fd513d5c5e6b63ad8e193c3fcdd0eeefcf9ab6df7ca5c5fbc622a63a33f7d
+oid sha256:43a0047c1f4849b7b6cea19c700df8596a7bc71c9ef39f6ce4cc6960374828c2
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fea756d925863317d55b7c25598d1b5b7a22bdd3a88f5ac4983f02069f2fe984
+oid sha256:cd72024597b2c3bf8343bfe8c1006caf70bcb94b9f5552f878b8f2c8272ff940
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.190843066918768,
+  "epoch": 0.19437719778763407,
   "eval_steps": 500,
-  "global_step": 10800,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1520,6 +1520,34 @@
       "learning_rate": 4.495493903516523e-05,
       "loss": 0.4372,
       "step": 10800
+    },
+    {
+      "epoch": 0.1917265996359845,
+      "grad_norm": 2.532017230987549,
+      "learning_rate": 4.4906834737193457e-05,
+      "loss": 0.3286,
+      "step": 10850
+    },
+    {
+      "epoch": 0.19261013235320104,
+      "grad_norm": 3.721505641937256,
+      "learning_rate": 4.485774871885493e-05,
+      "loss": 0.4082,
+      "step": 10900
+    },
+    {
+      "epoch": 0.19349366507041757,
+      "grad_norm": 2.2368271350860596,
+      "learning_rate": 4.4808662700516386e-05,
+      "loss": 0.4056,
+      "step": 10950
+    },
+    {
+      "epoch": 0.19437719778763407,
+      "grad_norm": 2.2011897563934326,
+      "learning_rate": 4.475957668217785e-05,
+      "loss": 0.4435,
+      "step": 11000
     }
   ],
   "logging_steps": 50,