Upload folder using huggingface_hub

metadata.json

@@ -0,0 +1,3 @@
+{
+    "max_value": 100000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:febd2c02ebeb100eb46072f2833000780021fa7902abcf0fefb1a47a14a2a87f
+size 345583444

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c361e019b8e4eb80d5e72063fdc877b52a90a2e6693d4cdc3be549981e78c305
+size 686562746

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4a500dafbd51bc7af82cd2cab5c06e4e2a4999422354d45c8e5e2645aa9be3
+size 1064

trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9574468085106383,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 37.91831970214844,
+      "learning_rate": 8.936170212765958e-05,
+      "loss": 0.4663,
+      "step": 10
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 4.650197982788086,
+      "learning_rate": 7.872340425531916e-05,
+      "loss": 0.2238,
+      "step": 20
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 3.5010766983032227,
+      "learning_rate": 6.808510638297873e-05,
+      "loss": 0.1096,
+      "step": 30
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 2.2222304344177246,
+      "learning_rate": 5.744680851063831e-05,
+      "loss": 0.0581,
+      "step": 40
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 5.912722110748291,
+      "learning_rate": 4.680851063829788e-05,
+      "loss": 0.0451,
+      "step": 50
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.5471988916397095,
+      "learning_rate": 3.617021276595745e-05,
+      "loss": 0.03,
+      "step": 60
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 5.3497138023376465,
+      "learning_rate": 2.5531914893617022e-05,
+      "loss": 0.0238,
+      "step": 70
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.6585015654563904,
+      "learning_rate": 1.4893617021276596e-05,
+      "loss": 0.0167,
+      "step": 80
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.7444632649421692,
+      "learning_rate": 4.255319148936171e-06,
+      "loss": 0.0133,
+      "step": 90
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 94,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc78ccef37572cfd5a3f4c62ef77fc6e920a96bd76814216f215583cdf89cb06
+size 4984