Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e66d01dfa2825d177f148be01e123916ae8ad822352fa3991ddadbd4df846c
+oid sha256:dd6622eb6d2f06c8805c5d1b53d336aea5992511f00713a9075b698b54fdcece
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2bbd20b1ee747110998970c84ba11f5687a29984dd589bbdc3cd412bf3cf865
+oid sha256:4fb0ac521b6f564d97622ade5cc991f93211f59608f70262ff6d645930ba004a
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f551f352c3582aab145c6f54f30ffbeee0b864e47c66aae4b8bf65aa86b3ab
+oid sha256:26cadf98409e0764d6e8fd5269af09ca75aa8d4f36721d4b135f9710aa32d59e
 size 14645

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c0caf2011a7cb0034062f49b1c20f2067d88b910ef9cf32d24c7e9ddd08314
+oid sha256:0463f6582fe857e6419932817a025a3e7560bae906a02d87b6dfe3b560ecd651
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32485110990795885,
+  "epoch": 0.4331348132106118,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -140,6 +140,50 @@
       "eval_samples_per_second": 112.28,
       "eval_steps_per_second": 7.022,
       "step": 3000
+    },
+    {
+      "epoch": 0.3519220357336221,
+      "grad_norm": 1.0289523601531982,
+      "learning_rate": 8.827287493232269e-05,
+      "loss": 3.7326,
+      "step": 3250
+    },
+    {
+      "epoch": 0.3789929615592853,
+      "grad_norm": 0.9764179587364197,
+      "learning_rate": 8.737051073813391e-05,
+      "loss": 3.6939,
+      "step": 3500
+    },
+    {
+      "epoch": 0.3789929615592853,
+      "eval_loss": 3.052320718765259,
+      "eval_runtime": 87.6344,
+      "eval_samples_per_second": 112.399,
+      "eval_steps_per_second": 7.029,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4060638873849486,
+      "grad_norm": 0.9247903227806091,
+      "learning_rate": 8.646814654394514e-05,
+      "loss": 3.6782,
+      "step": 3750
+    },
+    {
+      "epoch": 0.4331348132106118,
+      "grad_norm": 0.9769233465194702,
+      "learning_rate": 8.556578234975636e-05,
+      "loss": 3.6654,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4331348132106118,
+      "eval_loss": 3.0321156978607178,
+      "eval_runtime": 87.6462,
+      "eval_samples_per_second": 112.384,
+      "eval_steps_per_second": 7.028,
+      "step": 4000
     }
   ],
   "logging_steps": 250,
@@ -159,7 +203,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1083162230784000.0,
+  "total_flos": 1444216307712000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null