Training in progress, step 56591, checkpoint

last-checkpoint/README.md

@@ -1285,6 +1285,9 @@ You can finetune this model on your own dataset.
 | 0.9949 | 56300 | 0.3292        |
 | 0.9957 | 56350 | 0.3199        |
 | 0.9966 | 56400 | 0.284         |
+| 0.9975 | 56450 | 0.3286        |
+| 0.9984 | 56500 | 0.3321        |
+| 0.9993 | 56550 | 0.3073        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4747cc93084121a20f52f8b5b3fae00c2031a6d438b4dd7c030dc7e8652c32aa
+oid sha256:2514f1581b5b9bd9fa9821cba7f6f7b62f878d4ddfd7576926f1704f6c1e95af
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a01f3f6168f288a9f54b715fca053c4247ee3c93290ec1fa8d7523534d20340
+oid sha256:a5e371248185bdb849bd00f5451bd4f1ef5c657b5b435522ab3daa961723e945
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f4a9b315b1a20d2d787ee19f75f3a9099eeab81535c38061478be96f3a2307
+oid sha256:8c339021d6ff1b158aa54db8400835577e8079177f69a6e8e9c284454f93357a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122be002ed2c68d1f49408fb696a88fb75bec95372b6d4e67c49fa667ddaf90a
+oid sha256:e8f8c3cd37eb45ec4443c5f6b07ddb98f561f7a1fb9ca9c8f1407da98fd20681
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da795e3f463af8c3f55b378fcdaabc95ba9e2728665cb3652b390ac2ddc09ef8
+oid sha256:df25f25a96e4c735541738d3bda1505ccc91c4ea2bb1e15e5319dd7b86ce90b3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9966249050202329,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 56400,
+  "global_step": 56591,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7904,6 +7904,27 @@
       "learning_rate": 2.1008815848893604e-07,
       "loss": 0.284,
       "step": 56400
+    },
+    {
+      "epoch": 0.9975084377374495,
+      "grad_norm": 1.6319339275360107,
+      "learning_rate": 1.6100214015039955e-07,
+      "loss": 0.3286,
+      "step": 56450
+    },
+    {
+      "epoch": 0.998391970454666,
+      "grad_norm": 1.348299503326416,
+      "learning_rate": 1.119161218118631e-07,
+      "loss": 0.3321,
+      "step": 56500
+    },
+    {
+      "epoch": 0.9992755031718824,
+      "grad_norm": 1.5483179092407227,
+      "learning_rate": 6.283010347332666e-08,
+      "loss": 0.3073,
+      "step": 56550
     }
   ],
   "logging_steps": 50,
@@ -7918,7 +7939,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }