Training in progress, step 18200, checkpoint

last-checkpoint/README.md

@@ -1387,6 +1387,10 @@ You can finetune this model on your own dataset.
 | 0.3163 | 17900 | 0.4349        |
 | 0.3172 | 17950 | 0.3633        |
 | 0.3181 | 18000 | 0.3431        |
+| 0.3190 | 18050 | 0.3986        |
+| 0.3198 | 18100 | 0.3279        |
+| 0.3207 | 18150 | 0.3062        |
+| 0.3216 | 18200 | 0.2973        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:263f64c6b42b021ab57121e4e8f46faeb44f9ada3d36f39ddf425a7f3b1b4803
+oid sha256:5c561d22f3f5062bc767250ffdb3fa4a0f7bd3dbdb65e4c11cfceaa01995c64c
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da85b40c1057dfca9ce7e42a72509e47f1514b529359402a8efecc5d091d6623
+oid sha256:979b402a40bd2a435e70fee699ca07b55766750d192cbf2268122098c8ea3e92
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09d3ba87b7d0d8353c76a87036ebe87fa73b37b061f2207c2f20b469a834fce
+oid sha256:28d8ccebbb7f7b52e625ef2554e1cd3690dd81aea7ece9b35eeb250cf32f7566
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3082f8a8f0fc48d5193f80a2b266926a441fdb9c5495b02e03465c770eb219c
+oid sha256:1747e186a8b719e713dac067421a4083615d1c151147e0b1a41977c8731e3e98
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e92ded4afb81b531dc70334badaddabe870b22624bf7150b157aaa93592eb3b
+oid sha256:896e9fd82393923d4baed79b5528ea09727379e27a1318af2376e0aaf0f43d15
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3180717781979467,
+  "epoch": 0.32160590906681275,
   "eval_steps": 500,
-  "global_step": 18000,
+  "global_step": 18200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2528,6 +2528,34 @@
       "learning_rate": 3.7890479275883064e-05,
       "loss": 0.3431,
       "step": 18000
+    },
+    {
+      "epoch": 0.3189553109151632,
+      "grad_norm": 1.6438477039337158,
+      "learning_rate": 3.784139325754452e-05,
+      "loss": 0.3986,
+      "step": 18050
+    },
+    {
+      "epoch": 0.3198388436323797,
+      "grad_norm": 1.6794339418411255,
+      "learning_rate": 3.779230723920599e-05,
+      "loss": 0.3279,
+      "step": 18100
+    },
+    {
+      "epoch": 0.3207223763495962,
+      "grad_norm": 1.5067431926727295,
+      "learning_rate": 3.7743221220867445e-05,
+      "loss": 0.3062,
+      "step": 18150
+    },
+    {
+      "epoch": 0.32160590906681275,
+      "grad_norm": 1.6953719854354858,
+      "learning_rate": 3.7694135202528916e-05,
+      "loss": 0.2973,
+      "step": 18200
     }
   ],
   "logging_steps": 50,