Training in progress, step 24800, checkpoint

last-checkpoint/README.md

@@ -1519,6 +1519,10 @@ You can finetune this model on your own dataset.
 | 0.4329 | 24500 | 0.278         |
 | 0.4338 | 24550 | 0.4386        |
 | 0.4347 | 24600 | 0.4193        |
+| 0.4356 | 24650 | 0.367         |
+| 0.4365 | 24700 | 0.3474        |
+| 0.4373 | 24750 | 0.3116        |
+| 0.4382 | 24800 | 0.2733        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f521883c24fa0c5ef0d5496aed171da0d0aaf9518af226eda7a0624fd83f31
+oid sha256:d1a6814f8b5ec1634bc957286eb983b49496dec8c06da38d5b609edfe4943162
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7de91b8f4b5f9afea018786d14544bdbf97444a26a9894a6f78562cca048760
+oid sha256:5014e7c824b5bba9795a3854afd07633842628a9cdcb9a54a06ad696e1b4f903
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2902ca5c9eba1cc8519ae73c2f7885738abfe1dc8e6001f50fb19761dc55e0b
+oid sha256:cfdc511f69d97de8443ad30f266ce1fb3539b806724de4144228eaca4248f565
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b33249ab6bab1e060a0a22477da48a7f7b43ecee2e64e0ef287ea0d9219a4d
+oid sha256:335a5fd15f36238bc16955df172a43171379880e3bcb88eb14202c50efca1486
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074a86f28f57ef8a2c132a776cf6cef5fdfebd08cc63459240ea25fb180b3188
+oid sha256:e25f886cbcef3624ee21fe280a14d945057b01ddf68ca3820604e9ccd990e8d3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.43469809687052713,
+  "epoch": 0.4382322277393932,
   "eval_steps": 500,
-  "global_step": 24600,
+  "global_step": 24800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3452,6 +3452,34 @@
       "learning_rate": 3.141407001629656e-05,
       "loss": 0.4193,
       "step": 24600
+    },
+    {
+      "epoch": 0.43558162958774366,
+      "grad_norm": 1.150854468345642,
+      "learning_rate": 3.1364983997958025e-05,
+      "loss": 0.367,
+      "step": 24650
+    },
+    {
+      "epoch": 0.43646516230496013,
+      "grad_norm": 1.6972355842590332,
+      "learning_rate": 3.131589797961948e-05,
+      "loss": 0.3474,
+      "step": 24700
+    },
+    {
+      "epoch": 0.43734869502217666,
+      "grad_norm": 1.355474829673767,
+      "learning_rate": 3.126681196128095e-05,
+      "loss": 0.3116,
+      "step": 24750
+    },
+    {
+      "epoch": 0.4382322277393932,
+      "grad_norm": 1.4246526956558228,
+      "learning_rate": 3.121772594294242e-05,
+      "loss": 0.2733,
+      "step": 24800
     }
   ],
   "logging_steps": 50,