Training in progress, step 10800, checkpoint

last-checkpoint/README.md

@@ -1237,6 +1237,10 @@ You can finetune this model on your own dataset.
 | 0.1855 | 10500 | 0.3561        |
 | 0.1864 | 10550 | 0.4595        |
 | 0.1873 | 10600 | 0.4576        |
+| 0.1882 | 10650 | 0.4957        |
+| 0.1891 | 10700 | 0.3533        |
+| 0.1900 | 10750 | 0.5213        |
+| 0.1908 | 10800 | 0.4372        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898706945bff94a8c26029afbb9a8e57368208baa631e3d5379ac345b88c23e4
+oid sha256:6f408adec52fbb09d85249b52246fc558988060284c8e9e89545510e5f53f1fe
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3352beb06f35e0939e26a767db457defa58962b7981e5e0f19cce864164ac6
+oid sha256:f3a277a8a603891a188ecd4a7bff193d0e3832dc4f4e3f75b9504c7a244433a2
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d903a167ca6183c5f3c2025dbf11ab4c1f82f5752c7be9f632890f7d7664ba
+oid sha256:b39af6a910c9139a42774120919755175edcea033ab599451e3e8ba8327efe56
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cdde51625a60ddf478b829c5de2914d092bcbccf5cff85ea3fbaa0b25ddc285
+oid sha256:618fd513d5c5e6b63ad8e193c3fcdd0eeefcf9ab6df7ca5c5fbc622a63a33f7d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dcb2021f29c123c2e4518be6fa8ad522f1150b024c214ac74901399a553eb34
+oid sha256:fea756d925863317d55b7c25598d1b5b7a22bdd3a88f5ac4983f02069f2fe984
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18730893604990193,
+  "epoch": 0.190843066918768,
   "eval_steps": 500,
-  "global_step": 10600,
+  "global_step": 10800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1492,6 +1492,34 @@
       "learning_rate": 4.515128310851937e-05,
       "loss": 0.4576,
       "step": 10600
+    },
+    {
+      "epoch": 0.18819246876711845,
+      "grad_norm": 1.7272285223007202,
+      "learning_rate": 4.5102197090180835e-05,
+      "loss": 0.4957,
+      "step": 10650
+    },
+    {
+      "epoch": 0.18907600148433495,
+      "grad_norm": 1.529583215713501,
+      "learning_rate": 4.50531110718423e-05,
+      "loss": 0.3533,
+      "step": 10700
+    },
+    {
+      "epoch": 0.18995953420155148,
+      "grad_norm": 1.3267425298690796,
+      "learning_rate": 4.5004025053503764e-05,
+      "loss": 0.5213,
+      "step": 10750
+    },
+    {
+      "epoch": 0.190843066918768,
+      "grad_norm": 2.40889573097229,
+      "learning_rate": 4.495493903516523e-05,
+      "loss": 0.4372,
+      "step": 10800
     }
   ],
   "logging_steps": 50,