Training in progress, step 45800, checkpoint

last-checkpoint/README.md

@@ -1205,6 +1205,10 @@ You can finetune this model on your own dataset.
 | 0.8040 | 45500 | 0.306         |
 | 0.8049 | 45550 | 0.2888        |
 | 0.8058 | 45600 | 0.3101        |
+| 0.8067 | 45650 | 0.3148        |
+| 0.8075 | 45700 | 0.3975        |
+| 0.8084 | 45750 | 0.391         |
+| 0.8093 | 45800 | 0.3055        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dafa20b9ee08adc30b1b45605dd3458876a74a9a04d0a242b2d07bff11ffcfd4
+oid sha256:8cd5b7a0c7bbd9cd3c1ef7b582da35f4528606a4ac86bb04de178a7045ffef85
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e30656e2446cf01ec70d3edee1d105134bd862bca3236ab9a8c0b6f570bdcc1
+oid sha256:229981f79739c953722cfecdcfd1ea3bc38fb99e716343cc7272446d9e5bd67a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3642579a8c93faba29891bb437590b2fc3296379ded34bad3a25d71b44ae26dc
+oid sha256:0858441a43126cd8171b6b37146cb192258791649fae1dc1b48ff841ebace857
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803966f189174fdab2c5da9165b86bf3a54e44aa7c1402617aaf37d70a2c35b6
+oid sha256:791a23171b5f58ee5e75b5820d77158a2c7a8600431496a1df7bd6fb2c50e26f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db50723dd4d547a9dfd33b0f7da5dabf8169af1f05c3a349b52d1ff0ca949ad
+oid sha256:fb572362d72f52e385494a9e0afaacf81d8323c35f20a7a978751625112b3a58
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8057818381014649,
+  "epoch": 0.809315968970331,
   "eval_steps": 500,
-  "global_step": 45600,
+  "global_step": 45800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6392,6 +6392,34 @@
       "learning_rate": 1.0807759517778957e-05,
       "loss": 0.3101,
       "step": 45600
+    },
+    {
+      "epoch": 0.8066653708186814,
+      "grad_norm": 1.2750502824783325,
+      "learning_rate": 1.075867349944042e-05,
+      "loss": 0.3148,
+      "step": 45650
+    },
+    {
+      "epoch": 0.8075489035358979,
+      "grad_norm": 2.6815085411071777,
+      "learning_rate": 1.0709587481101884e-05,
+      "loss": 0.3975,
+      "step": 45700
+    },
+    {
+      "epoch": 0.8084324362531145,
+      "grad_norm": 1.3361300230026245,
+      "learning_rate": 1.0660501462763347e-05,
+      "loss": 0.391,
+      "step": 45750
+    },
+    {
+      "epoch": 0.809315968970331,
+      "grad_norm": 1.438496470451355,
+      "learning_rate": 1.061141544442481e-05,
+      "loss": 0.3055,
+      "step": 45800
     }
   ],
   "logging_steps": 50,