Upload checkpoint-1808

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0030169b4494b32139d9842582ba7941c21471e4318e7cf6e3b61eae2b7282e
+oid sha256:da7b863312662a189b621a743f70d64ac566be98825f036d664bf2fafd16b1cc
 size 430911284

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8923ab68580d1c142cba2bba36030ec1520bcb69ec900ecd49537a5854a4eab
+size 861942330

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bd2edd8262caf8450fadd8062730eafdeeadcf2d447ece8931b2e97c99fe31
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9873e0eecaab0b93619f87dcbf25cba5323140778efbc8545ef9e6bdeea0ba78
+size 1064

trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1808,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1061946902654867,
+      "grad_norm": 1.541396141052246,
+      "learning_rate": 1.5575221238938054e-05,
+      "loss": 0.1432,
+      "step": 500
+    },
+    {
+      "epoch": 2.2123893805309733,
+      "grad_norm": 0.7666749954223633,
+      "learning_rate": 1.1150442477876106e-05,
+      "loss": 0.0492,
+      "step": 1000
+    },
+    {
+      "epoch": 3.3185840707964602,
+      "grad_norm": 0.07702745497226715,
+      "learning_rate": 6.72566371681416e-06,
+      "loss": 0.0245,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2260,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 536680831748148.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14fc2f8c2a9a53f101ab29d3bb93824b292668774ad1870ae9ca65667e3d75d
+size 5048