Training in progress, step 15200, checkpoint

last-checkpoint/README.md

@@ -1327,6 +1327,10 @@ You can finetune this model on your own dataset.
 | 0.2633 | 14900 | 0.406         |
 | 0.2642 | 14950 | 0.357         |
 | 0.2651 | 15000 | 0.2855        |
+| 0.2659 | 15050 | 0.4424        |
+| 0.2668 | 15100 | 0.352         |
+| 0.2677 | 15150 | 0.3638        |
+| 0.2686 | 15200 | 0.3727        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a5255fda70735f530277b068143dfdac403e8121852574084f116cd8a54ad2
+oid sha256:585fb1254320abf5fa3fead82b5bb8bfb1adda02efcaf21fd3bca945c95bb8cd
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6061f93c451e2da3513d0e7ebb36b42a40ee13e63c2294272c5bca7237bb74f6
+oid sha256:533d32af8daf9f72c2f5acae406ece041eab382d9e444ec8876783f13534e8d9
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58d6a61e95480d63adba518dcc060210f3fb21899a87b9a86415b16500e0e3bf
+oid sha256:91bcb70f5dde9b132a8f4813819563f3e4a3ffe0599080085097bf651c34654e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b117d26681ce36f6295204f3c0c1542a5dbd8eba633804a8fd8e040b3e8c6050
+oid sha256:30577b072974c10d385ba88013a64c7f41f9003dbd098b2eb085609eff3dcb24
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647cbe535a4ae95aadfbebe85aa748dcd49df21d2f520f23e9e1a18d456097d
+oid sha256:9df63d8b4b8f4f625d8a4112d79b9bbc2733e8272c655434f7bca9c2ec612884
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2650598151649556,
+  "epoch": 0.26859394603382164,
   "eval_steps": 500,
-  "global_step": 15000,
+  "global_step": 15200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2108,6 +2108,34 @@
       "learning_rate": 4.0834658655828475e-05,
       "loss": 0.2855,
       "step": 15000
+    },
+    {
+      "epoch": 0.26594334788217205,
+      "grad_norm": 1.8597488403320312,
+      "learning_rate": 4.078557263748994e-05,
+      "loss": 0.4424,
+      "step": 15050
+    },
+    {
+      "epoch": 0.2668268805993886,
+      "grad_norm": 1.651663899421692,
+      "learning_rate": 4.0736486619151405e-05,
+      "loss": 0.352,
+      "step": 15100
+    },
+    {
+      "epoch": 0.2677104133166051,
+      "grad_norm": 1.452006459236145,
+      "learning_rate": 4.068740060081286e-05,
+      "loss": 0.3638,
+      "step": 15150
+    },
+    {
+      "epoch": 0.26859394603382164,
+      "grad_norm": 2.7887187004089355,
+      "learning_rate": 4.063831458247433e-05,
+      "loss": 0.3727,
+      "step": 15200
     }
   ],
   "logging_steps": 50,