Training in progress, step 10600, checkpoint

last-checkpoint/README.md

@@ -1233,6 +1233,10 @@ You can finetune this model on your own dataset.
 | 0.1820 | 10300 | 0.3565        |
 | 0.1829 | 10350 | 0.4409        |
 | 0.1838 | 10400 | 0.3762        |
+| 0.1847 | 10450 | 0.4571        |
+| 0.1855 | 10500 | 0.3561        |
+| 0.1864 | 10550 | 0.4595        |
+| 0.1873 | 10600 | 0.4576        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e173a418a6557a53411f35be06de499d8fc58209e23cd022b66875c6fc5b0ae3
+oid sha256:898706945bff94a8c26029afbb9a8e57368208baa631e3d5379ac345b88c23e4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f9ee877e3fc6c79f0984700034054c52886bebbe530aecf764a3bd0fec0227
+oid sha256:aa3352beb06f35e0939e26a767db457defa58962b7981e5e0f19cce864164ac6
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e3c346ce1d7e857e6a391133332aa5169f5fc12741629168a0c8fad4aa8ade
+oid sha256:64d903a167ca6183c5f3c2025dbf11ab4c1f82f5752c7be9f632890f7d7664ba
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dcdfe9f3f1d3b35aba345a67f9e5702ec3b3998d6ddccfa8925c3c66df7986e
+oid sha256:3cdde51625a60ddf478b829c5de2914d092bcbccf5cff85ea3fbaa0b25ddc285
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba07f8b635a7f5cbd77a454bf0384278026397ef33c00d176608de8376e15fc
+oid sha256:9dcb2021f29c123c2e4518be6fa8ad522f1150b024c214ac74901399a553eb34
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18377480518103587,
+  "epoch": 0.18730893604990193,
   "eval_steps": 500,
-  "global_step": 10400,
+  "global_step": 10600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1464,6 +1464,34 @@
       "learning_rate": 4.534762718187352e-05,
       "loss": 0.3762,
       "step": 10400
+    },
+    {
+      "epoch": 0.18465833789825237,
+      "grad_norm": 3.560997247695923,
+      "learning_rate": 4.529854116353498e-05,
+      "loss": 0.4571,
+      "step": 10450
+    },
+    {
+      "epoch": 0.1855418706154689,
+      "grad_norm": 2.0075438022613525,
+      "learning_rate": 4.524945514519645e-05,
+      "loss": 0.3561,
+      "step": 10500
+    },
+    {
+      "epoch": 0.1864254033326854,
+      "grad_norm": 2.405439853668213,
+      "learning_rate": 4.5200369126857906e-05,
+      "loss": 0.4595,
+      "step": 10550
+    },
+    {
+      "epoch": 0.18730893604990193,
+      "grad_norm": 1.6211732625961304,
+      "learning_rate": 4.515128310851937e-05,
+      "loss": 0.4576,
+      "step": 10600
     }
   ],
   "logging_steps": 50,