Training in progress, step 17400, checkpoint

last-checkpoint/README.md

@@ -1371,6 +1371,10 @@ You can finetune this model on your own dataset.
 | 0.3022 | 17100 | 0.4207        |
 | 0.3031 | 17150 | 0.3849        |
 | 0.3039 | 17200 | 0.3272        |
+| 0.3048 | 17250 | 0.3037        |
+| 0.3057 | 17300 | 0.2924        |
+| 0.3066 | 17350 | 0.4029        |
+| 0.3075 | 17400 | 0.5016        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8aa8eabf0bd95daa104946b416f3292c9a92c6053a47e54e8098083f61f3874
+oid sha256:45090e53ca13162f5dfed87da6ebea51548a6f3908cbbefc66a73c68e67f368f
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550870691770e56b635695a47badd3d85105a2abddd01d2f68ac682eb4779cfb
+oid sha256:5ca6aad37af14fa05240de5a73f6854c9f991ab7d94bccdddb3bd4a0e3ff149d
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9642b48564b74a9ef3023b3677305007ed89dfb95240067ad9d1be72f7d2692a
+oid sha256:23fe6d223e7616989ffc698a28faceb780fedfcab150f455b3003f3664a9d548
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c157b3717ebad1d1c4deed2f4a1e630570eeaf89e281bb553ac41881d02a28e
+oid sha256:c2780f904a141afb4c77d183d8b90351cd99dc707535728f23c895b86a7cd2bb
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcdcffdcd8983b3d6481c27ecbd4b8783b8846e8b39268fee55aae8ba8b88e41
+oid sha256:9d388bf9897e62191d89d430ec5647330caf741ec214058515a40e21a614b139
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3039352547224824,
+  "epoch": 0.30746938559134845,
   "eval_steps": 500,
-  "global_step": 17200,
+  "global_step": 17400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2416,6 +2416,34 @@
       "learning_rate": 3.867585556929964e-05,
       "loss": 0.3272,
       "step": 17200
+    },
+    {
+      "epoch": 0.30481878743969887,
+      "grad_norm": 1.5218919515609741,
+      "learning_rate": 3.862676955096111e-05,
+      "loss": 0.3037,
+      "step": 17250
+    },
+    {
+      "epoch": 0.3057023201569154,
+      "grad_norm": 1.5864076614379883,
+      "learning_rate": 3.857768353262257e-05,
+      "loss": 0.2924,
+      "step": 17300
+    },
+    {
+      "epoch": 0.3065858528741319,
+      "grad_norm": 1.8895894289016724,
+      "learning_rate": 3.852859751428403e-05,
+      "loss": 0.4029,
+      "step": 17350
+    },
+    {
+      "epoch": 0.30746938559134845,
+      "grad_norm": 1.4156498908996582,
+      "learning_rate": 3.8479511495945495e-05,
+      "loss": 0.5016,
+      "step": 17400
     }
   ],
   "logging_steps": 50,