Training in progress, step 43400, checkpoint

last-checkpoint/README.md

@@ -1383,6 +1383,10 @@ You can finetune this model on your own dataset.
 | 0.7616 | 43100 | 0.3065        |
 | 0.7625 | 43150 | 0.3252        |
 | 0.7634 | 43200 | 0.2418        |
+| 0.7643 | 43250 | 0.4002        |
+| 0.7651 | 43300 | 0.3379        |
+| 0.7660 | 43350 | 0.3574        |
+| 0.7669 | 43400 | 0.3664        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c0c9a0b1262140e82733d51fe5efff8b0e4a0984fb8df6ff90e910c2afd4ab8
+oid sha256:a485f5135dbf7941d9dcd8b8fc45b11939ecd8d30155eb2ca9556cbce39f7319
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83e7c31a2c3e589b653cbf5d4ef5a6592e9733967f1d138904e5d044c5d5848
+oid sha256:c10cdbf25dd441e6bb32bd4c10385f309c62ad905ef0798b745b11cff9a1720f
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9579fa0231ee8c937aa4751dd1de3d5d49af35716658dc3ccf0f0e2d1f420d45
+oid sha256:83302e5118655d454ab8451ea7900b6308bc7d6e9ac3f9707bf02a76f063afd4
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e689eacce1d8ee34e87120437a30d68097f39c37749fc244a0885289f69d33c
+oid sha256:0daa70100b5915dc065db5369cf2e73a99b71868d4f3cbde645519f2b7941b1f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0456f284ad1b7efca7712b00a843898c6fb37f599b5c1b8ffce60a83dcfa662
+oid sha256:84574c094748f0062cf1157bf6aedafea7577270e5b0318bc110f644f7a5512b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.763372267675072,
+  "epoch": 0.766906398543938,
   "eval_steps": 500,
-  "global_step": 43200,
+  "global_step": 43400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6056,6 +6056,34 @@
       "learning_rate": 1.3162906677661935e-05,
       "loss": 0.2418,
       "step": 43200
+    },
+    {
+      "epoch": 0.7642558003922886,
+      "grad_norm": 1.6417291164398193,
+      "learning_rate": 1.31138206593234e-05,
+      "loss": 0.4002,
+      "step": 43250
+    },
+    {
+      "epoch": 0.765139333109505,
+      "grad_norm": 1.5653693675994873,
+      "learning_rate": 1.3064734640984863e-05,
+      "loss": 0.3379,
+      "step": 43300
+    },
+    {
+      "epoch": 0.7660228658267215,
+      "grad_norm": 1.279615879058838,
+      "learning_rate": 1.3015648622646326e-05,
+      "loss": 0.3574,
+      "step": 43350
+    },
+    {
+      "epoch": 0.766906398543938,
+      "grad_norm": 1.693057894706726,
+      "learning_rate": 1.2966562604307789e-05,
+      "loss": 0.3664,
+      "step": 43400
     }
   ],
   "logging_steps": 50,