Training in progress, step 43600, checkpoint

last-checkpoint/README.md

@@ -1387,6 +1387,10 @@ You can finetune this model on your own dataset.
 | 0.7651 | 43300 | 0.3379        |
 | 0.7660 | 43350 | 0.3574        |
 | 0.7669 | 43400 | 0.3664        |
+| 0.7678 | 43450 | 0.3274        |
+| 0.7687 | 43500 | 0.2443        |
+| 0.7696 | 43550 | 0.2998        |
+| 0.7704 | 43600 | 0.3619        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a485f5135dbf7941d9dcd8b8fc45b11939ecd8d30155eb2ca9556cbce39f7319
+oid sha256:582d7207fbae78615ca0e36023c8110cb512dfcbe185f219cdbef0f8c88f6707
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c10cdbf25dd441e6bb32bd4c10385f309c62ad905ef0798b745b11cff9a1720f
+oid sha256:38bd1bddb06afe7bdefce01320f5544bdf1fc670f6d4527df71f8729233aad04
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83302e5118655d454ab8451ea7900b6308bc7d6e9ac3f9707bf02a76f063afd4
+oid sha256:5ec0767005b2ab07f761617d9b9ec8dd40511cb9cacfed18b38312ca707add4f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0daa70100b5915dc065db5369cf2e73a99b71868d4f3cbde645519f2b7941b1f
+oid sha256:f1a993fdfb900c15fe63d9947d4534a020649b78ba75ceb8b6036bf3ab2fc94f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84574c094748f0062cf1157bf6aedafea7577270e5b0318bc110f644f7a5512b
+oid sha256:c6d4bed09415fa87d626fafe2a8875f4460b02e4d1ca2a4d5c36913f61694143
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.766906398543938,
+  "epoch": 0.7704405294128042,
   "eval_steps": 500,
-  "global_step": 43400,
+  "global_step": 43600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6084,6 +6084,34 @@
       "learning_rate": 1.2966562604307789e-05,
       "loss": 0.3664,
       "step": 43400
+    },
+    {
+      "epoch": 0.7677899312611546,
+      "grad_norm": 2.931711196899414,
+      "learning_rate": 1.2917476585969254e-05,
+      "loss": 0.3274,
+      "step": 43450
+    },
+    {
+      "epoch": 0.7686734639783711,
+      "grad_norm": 1.3495726585388184,
+      "learning_rate": 1.2868390567630716e-05,
+      "loss": 0.2443,
+      "step": 43500
+    },
+    {
+      "epoch": 0.7695569966955876,
+      "grad_norm": 1.4437354803085327,
+      "learning_rate": 1.281930454929218e-05,
+      "loss": 0.2998,
+      "step": 43550
+    },
+    {
+      "epoch": 0.7704405294128042,
+      "grad_norm": 4.394979000091553,
+      "learning_rate": 1.2770218530953642e-05,
+      "loss": 0.3619,
+      "step": 43600
     }
   ],
   "logging_steps": 50,