Training in progress, step 52200, checkpoint

last-checkpoint/README.md

@@ -1197,6 +1197,10 @@ You can finetune this model on your own dataset.
 | 0.9171 | 51900 | 0.3976        |
 | 0.9180 | 51950 | 0.2939        |
 | 0.9189 | 52000 | 0.3193        |
+| 0.9198 | 52050 | 0.2988        |
+| 0.9206 | 52100 | 0.2286        |
+| 0.9215 | 52150 | 0.371         |
+| 0.9224 | 52200 | 0.2825        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64df739ab78548e5d75f993ab6041c207785adcb30fa9a57cf9234173976387d
+oid sha256:dcce17b7b84aa84d9a62e4ecacf9221e386cc1f4a8fd8f1ff065fb84d8b66600
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab3798d7d967dd27d94d9da8c3b443a2ae8d98157d0a447c72ba241256385ef3
+oid sha256:3b1907993a4836b8d7f68772a56e92f265d1d0b880c0f389e3d9a3261d2c18d6
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf77e2ef33f60ef48f8a5fc09cb1943760ae6ba4d88634c23d14cfcf6cad117
+oid sha256:7eb456525d851480624b8b851b2b4e427ee862f93eba28a337891329169059e3
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12597bbc3e3311f727af17ce6725c67e2c62ce8d20a5da4fcf3ead6fc2b4cd3a
+oid sha256:8f8d439a57eb96c40411a5c7daa3d2c6f4bcb1ca85fe20f7f71f85e34ad3c1e4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69967b924386ed794e36fcb2fe2f94715b55410c1d3076df0af1214b0c14df7b
+oid sha256:8195c12f983d26de39eb9400cc5a62a3f600dcf25125907830ba8d58cfd3e0c0
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9188740259051793,
+  "epoch": 0.9224081567740453,
   "eval_steps": 500,
-  "global_step": 52000,
+  "global_step": 52200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7288,6 +7288,34 @@
       "learning_rate": 4.527694331546602e-06,
       "loss": 0.3193,
       "step": 52000
+    },
+    {
+      "epoch": 0.9197575586223958,
+      "grad_norm": 1.4950217008590698,
+      "learning_rate": 4.478608313208066e-06,
+      "loss": 0.2988,
+      "step": 52050
+    },
+    {
+      "epoch": 0.9206410913396124,
+      "grad_norm": 1.5405720472335815,
+      "learning_rate": 4.42952229486953e-06,
+      "loss": 0.2286,
+      "step": 52100
+    },
+    {
+      "epoch": 0.9215246240568288,
+      "grad_norm": 1.5918203592300415,
+      "learning_rate": 4.3804362765309926e-06,
+      "loss": 0.371,
+      "step": 52150
+    },
+    {
+      "epoch": 0.9224081567740453,
+      "grad_norm": 1.2329323291778564,
+      "learning_rate": 4.331350258192457e-06,
+      "loss": 0.2825,
+      "step": 52200
     }
   ],
   "logging_steps": 50,