Training in progress, step 51800, checkpoint

last-checkpoint/README.md

@@ -1189,10 +1189,10 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step  | Training Loss |
 |:------:|:-----:|:-------------:|
-| 0.9092 | 51450 | 0.2997        |
-| 0.9100 | 51500 | 0.2247        |
-| 0.9109 | 51550 | 0.2918        |
-| 0.9118 | 51600 | 0.3295        |
+| 0.9127 | 51650 | 0.2493        |
+| 0.9136 | 51700 | 0.3088        |
+| 0.9145 | 51750 | 0.2287        |
+| 0.9153 | 51800 | 0.2067        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeecd8d9471d7a0b6627d01abbb6ab9354f23702be741b49535069a09a804f63
+oid sha256:8adbf03525b39d3cbba1bbdde2da90cb7be2d698601f862e040d6383edf785e8
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a86535350dee0d838aabde4505a86ae7f966c06b02b476617bf119348d925b
+oid sha256:ddba7d83c634a4905db07a12f6761ec90e0847d3c3a75cb805e5a2c45f6f055e
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a589e7cc1c3f0f337824a3d6a8bc421970447f40e56c215be58c6b1d6c52a5a0
+oid sha256:ed3acf2d762800b6693f2eadfe02d38f79ee54f3a4fcf7d7f00a5e20954d4a73
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39475f4e00274ea95478c0aa6d264be5db3bd87ad877f934d4b5cd1f7f759e82
+oid sha256:e37c94dad9c27aa070c66f020f85050e7628adbe8df381c470c2f01ed333d243
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0adae6525b0259ff389512f804b95631a5bbbd0e13a53824c06deb281fe18e7
+oid sha256:ad4fc38cbd3a40df512cafd836390b147d408874f4ecc602c76931ee4bd316f8
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9118057641674471,
+  "epoch": 0.9153398950363132,
   "eval_steps": 500,
-  "global_step": 51600,
+  "global_step": 51800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7232,6 +7232,34 @@
       "learning_rate": 4.920382478254894e-06,
       "loss": 0.3295,
       "step": 51600
+    },
+    {
+      "epoch": 0.9126892968846636,
+      "grad_norm": 1.4896866083145142,
+      "learning_rate": 4.871296459916358e-06,
+      "loss": 0.2493,
+      "step": 51650
+    },
+    {
+      "epoch": 0.9135728296018801,
+      "grad_norm": 4.590723037719727,
+      "learning_rate": 4.8222104415778216e-06,
+      "loss": 0.3088,
+      "step": 51700
+    },
+    {
+      "epoch": 0.9144563623190967,
+      "grad_norm": 1.653506875038147,
+      "learning_rate": 4.7731244232392845e-06,
+      "loss": 0.2287,
+      "step": 51750
+    },
+    {
+      "epoch": 0.9153398950363132,
+      "grad_norm": 1.7086869478225708,
+      "learning_rate": 4.724038404900748e-06,
+      "loss": 0.2067,
+      "step": 51800
     }
   ],
   "logging_steps": 50,

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1eb037399f5df91069f9b474c7a40c3e0d7a309caabb274d665499c0377b52
+oid sha256:6c6646a21e44808e01dce45e09fa7fbd1fffd2b29b00d00306ba050ea82ef5a2
 size 5560