Training in progress, step 48800, checkpoint

last-checkpoint/README.md

@@ -1265,6 +1265,10 @@ You can finetune this model on your own dataset.
 | 0.8570 | 48500 | 0.3492        |
 | 0.8579 | 48550 | 0.2794        |
 | 0.8588 | 48600 | 0.2854        |
+| 0.8597 | 48650 | 0.2664        |
+| 0.8606 | 48700 | 0.3028        |
+| 0.8614 | 48750 | 0.2579        |
+| 0.8623 | 48800 | 0.3404        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f97e4be59707659beabd834e11f6a65a7292265dfb49c2caf9bc89b0c6716a
+oid sha256:36dc7c9e83fd465b92a2847be177b9eb428689ac2977e5e232b38d92574447f6
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48984ae26e348d11908c5f2745c34cd2def85ea7c810d9fbea301d1fb62f8737
+oid sha256:476cfc5664418f0c7219fe39c91775cf7ee5aec7d0f1d77a8008aa21455285b8
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b99c2c71b3197a1fb7e795c175200808e384737d0136671189f7f54df62c39
+oid sha256:7c91689e6fe6ea5ac1e3ed99062e8d26595b040c06b11772caa18d4fe3ffb3e8
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d2345a7bbddb12fb6a365e62bd73e47296785a601a5379725821a73d3794f3
+oid sha256:e7d183fbaa9612fc768da7cf7cefd13466b61ea27398ff0fc8e2f5977752f4ef
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53bf9eae9141600b1f20ec91bc52ae342d59856e71a200d65bc37505fde53a5f
+oid sha256:c86d99e394985101a11e9cbc029a6edaca303ea24f38f1f70ed88d32b2ae0eb0
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.858793801134456,
+  "epoch": 0.862327932003322,
   "eval_steps": 500,
-  "global_step": 48600,
+  "global_step": 48800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6812,6 +6812,34 @@
       "learning_rate": 7.86358013783354e-06,
       "loss": 0.2854,
       "step": 48600
+    },
+    {
+      "epoch": 0.8596773338516726,
+      "grad_norm": 1.4077606201171875,
+      "learning_rate": 7.814494119495003e-06,
+      "loss": 0.2664,
+      "step": 48650
+    },
+    {
+      "epoch": 0.8605608665688891,
+      "grad_norm": 1.417729139328003,
+      "learning_rate": 7.765408101156466e-06,
+      "loss": 0.3028,
+      "step": 48700
+    },
+    {
+      "epoch": 0.8614443992861056,
+      "grad_norm": 1.0813167095184326,
+      "learning_rate": 7.716322082817931e-06,
+      "loss": 0.2579,
+      "step": 48750
+    },
+    {
+      "epoch": 0.862327932003322,
+      "grad_norm": 2.008650064468384,
+      "learning_rate": 7.667236064479394e-06,
+      "loss": 0.3404,
+      "step": 48800
     }
   ],
   "logging_steps": 50,