Training in progress, step 53800, checkpoint

last-checkpoint/README.md

@@ -1229,6 +1229,10 @@ You can finetune this model on your own dataset.
 | 0.9454 | 53500 | 0.3135        |
 | 0.9463 | 53550 | 0.2813        |
 | 0.9471 | 53600 | 0.2333        |
+| 0.9480 | 53650 | 0.3022        |
+| 0.9489 | 53700 | 0.303         |
+| 0.9498 | 53750 | 0.2651        |
+| 0.9507 | 53800 | 0.3384        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46322e2fdae84cb4d149624b40324ba603107423e0ed811b11c103af6014e1e4
+oid sha256:32883cc8380b5551ef8b0cc0e17f87142260e9e4e1f436103ef31fd1a32a59e7
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068f22c1d711e17dfced7140337b436095f34a8fa926c1703ed0a4e7970380ec
+oid sha256:fdb8e455fcefebf6e65cc70da46171fa65d7d3724795dbd5ebe39eb526ed73b1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738e43c027de9571a26dc41c2c90188ad15bc024b7fa4548c553209c415b7ff9
+oid sha256:aa1d10cc07f26722031d44ae9ed204b0fd93f2944405a821aaf7d32c94a690ee
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41033b29e66c9e9264898026bd8259ffc51d8197a6199f012e6c4fab4d2b8853
+oid sha256:fcb8b2220528541cf3e98738aad3670d259e0a7ccf7ba003e8c4a04ead86cd5e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225f37a4049625453028403228c6e91c80694c7d0b9a5b2f9a1f983bafdfc1df
+oid sha256:e02c7889d99a6f23f73ba0719fb9e5f5f23bfc59153bd58184aaf763c67dfbef
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9471470728561079,
+  "epoch": 0.9506812037249739,
   "eval_steps": 500,
-  "global_step": 53600,
+  "global_step": 53800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7512,6 +7512,34 @@
       "learning_rate": 2.9579234650802064e-06,
       "loss": 0.2333,
       "step": 53600
+    },
+    {
+      "epoch": 0.9480306055733244,
+      "grad_norm": 3.0708839893341064,
+      "learning_rate": 2.9088374467416706e-06,
+      "loss": 0.3022,
+      "step": 53650
+    },
+    {
+      "epoch": 0.9489141382905409,
+      "grad_norm": 1.637635588645935,
+      "learning_rate": 2.859751428403134e-06,
+      "loss": 0.303,
+      "step": 53700
+    },
+    {
+      "epoch": 0.9497976710077575,
+      "grad_norm": 2.5479607582092285,
+      "learning_rate": 2.8106654100645974e-06,
+      "loss": 0.2651,
+      "step": 53750
+    },
+    {
+      "epoch": 0.9506812037249739,
+      "grad_norm": 4.394486427307129,
+      "learning_rate": 2.761579391726061e-06,
+      "loss": 0.3384,
+      "step": 53800
     }
   ],
   "logging_steps": 50,