Training in progress, step 52400, checkpoint

last-checkpoint/README.md

@@ -1201,6 +1201,10 @@ You can finetune this model on your own dataset.
 | 0.9206 | 52100 | 0.2286        |
 | 0.9215 | 52150 | 0.371         |
 | 0.9224 | 52200 | 0.2825        |
+| 0.9233 | 52250 | 0.3728        |
+| 0.9242 | 52300 | 0.3196        |
+| 0.9251 | 52350 | 0.3322        |
+| 0.9259 | 52400 | 0.3258        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcce17b7b84aa84d9a62e4ecacf9221e386cc1f4a8fd8f1ff065fb84d8b66600
+oid sha256:2b6ccee8235180e0fcb744d9c9527b2c600512f7ecc4b3d25488b384822838a3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1907993a4836b8d7f68772a56e92f265d1d0b880c0f389e3d9a3261d2c18d6
+oid sha256:002e9ce3d93da778bb4fe1c95037789e052796647a41c67b89002e6d3a8a69ff
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb456525d851480624b8b851b2b4e427ee862f93eba28a337891329169059e3
+oid sha256:3763a2915178d87a90c93bc33c9a17dd8d33e1ee286d4f530459bdee03d15b6d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8d439a57eb96c40411a5c7daa3d2c6f4bcb1ca85fe20f7f71f85e34ad3c1e4
+oid sha256:0315f631d073b9e84cefc9abe7ee2e75af036769039c7a2bf20f3d81a5e6f752
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8195c12f983d26de39eb9400cc5a62a3f600dcf25125907830ba8d58cfd3e0c0
+oid sha256:acf725a620db2293e4b5f5ac9e35cb4f2f88cf44a5a0884c22a06b906efee164
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9224081567740453,
+  "epoch": 0.9259422876429114,
   "eval_steps": 500,
-  "global_step": 52200,
+  "global_step": 52400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7316,6 +7316,34 @@
       "learning_rate": 4.331350258192457e-06,
       "loss": 0.2825,
       "step": 52200
+    },
+    {
+      "epoch": 0.9232916894912618,
+      "grad_norm": 1.2270597219467163,
+      "learning_rate": 4.28226423985392e-06,
+      "loss": 0.3728,
+      "step": 52250
+    },
+    {
+      "epoch": 0.9241752222084784,
+      "grad_norm": 1.8672150373458862,
+      "learning_rate": 4.233178221515384e-06,
+      "loss": 0.3196,
+      "step": 52300
+    },
+    {
+      "epoch": 0.9250587549256949,
+      "grad_norm": 1.6005786657333374,
+      "learning_rate": 4.184092203176848e-06,
+      "loss": 0.3322,
+      "step": 52350
+    },
+    {
+      "epoch": 0.9259422876429114,
+      "grad_norm": 1.4158750772476196,
+      "learning_rate": 4.135006184838311e-06,
+      "loss": 0.3258,
+      "step": 52400
     }
   ],
   "logging_steps": 50,