Upload 6 files

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5323811668ca9bf66b8206bef1809ecd14bf120e34c462f3606af8278880009b
+size 402807738

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb6017ec763ab32c6ec5c6eb4c3cd2ef1a24407bcb5ccb6d0a4ce7f14e058e0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e94ee387cdc1c0c2110bb28bc6a17f539dbbde85d51ff9961b2ca5845e54c5
+size 1064

trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08756567425569177,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.0906548500061035,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 4.9136,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.1564817428588867,
+      "learning_rate": 9.524135262330098e-05,
+      "loss": 4.051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.0015352964401245,
+      "learning_rate": 8.644843137107059e-05,
+      "loss": 3.0966,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9585821032524109,
+      "learning_rate": 7.408768370508576e-05,
+      "loss": 2.8687,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9819431900978088,
+      "learning_rate": 5.9369065729286245e-05,
+      "loss": 2.9512,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.0021209716796875,
+      "learning_rate": 4.373333832178478e-05,
+      "loss": 2.6709,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.7910182476043701,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.5329,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.9146462678909302,
+      "learning_rate": 1.5772644703565565e-05,
+      "loss": 2.289,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.7808576822280884,
+      "learning_rate": 6.184665997806832e-06,
+      "loss": 2.3726,
+      "step": 90
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.4270635843276978,
+      "learning_rate": 8.856374635655695e-07,
+      "loss": 2.1876,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "total_flos": 220661981798400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199cd782aa26f4c59cb15a86ef5f1e478f199cc3792924b9bc5b27042309343a
+size 4920