Upload 11 files

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67179c0dc19199352d428893b61450ae9f00af3404a84b2024eb15fe36461025
+oid sha256:35b6e2f35655e89e650361d09e006b75dc7f2974259ee18e5e9c992d3c91f599
 size 90867952

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461c599bbd485ca924159ca125f5b6ab7935228633e7dbaee36ba9aac246268c
+size 1193234

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66f53273236860d66701199883221bdb68ebc91f097aab8dbb32e3e6a8d8a2a
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09b1d190cbb4d98f5bfdd3ab1793e385b74b5eef08d580a77ac879bc4ff2d94
+size 1064

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.052040886133909225,
+  "best_model_checkpoint": "ckpt/checkpoint-200",
+  "epoch": 2.824858757062147,
+  "eval_steps": 200,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2824858757062147,
+      "grad_norm": 0.08298324048519135,
+      "learning_rate": 0.00029152542372881354,
+      "loss": 0.1901,
+      "step": 100
+    },
+    {
+      "epoch": 0.5649717514124294,
+      "grad_norm": 0.11693409830331802,
+      "learning_rate": 0.0002830508474576271,
+      "loss": 0.0624,
+      "step": 200
+    },
+    {
+      "epoch": 0.5649717514124294,
+      "eval_accuracy": 0.9860834990059643,
+      "eval_f1": 0.9891354958870091,
+      "eval_loss": 0.052040886133909225,
+      "eval_precision": 0.9869908626297041,
+      "eval_recall": 0.9912894695909161,
+      "eval_runtime": 12.1769,
+      "eval_samples_per_second": 826.154,
+      "eval_steps_per_second": 6.488,
+      "step": 200
+    },
+    {
+      "epoch": 0.847457627118644,
+      "grad_norm": 0.10722041875123978,
+      "learning_rate": 0.00027457627118644066,
+      "loss": 0.0562,
+      "step": 300
+    },
+    {
+      "epoch": 1.1299435028248588,
+      "grad_norm": 0.08397164940834045,
+      "learning_rate": 0.0002661016949152542,
+      "loss": 0.0524,
+      "step": 400
+    },
+    {
+      "epoch": 1.1299435028248588,
+      "eval_accuracy": 0.9874751491053678,
+      "eval_f1": 0.9902219462983083,
+      "eval_loss": 0.04475295916199684,
+      "eval_precision": 0.9880749574105622,
+      "eval_recall": 0.9923782858920517,
+      "eval_runtime": 11.6899,
+      "eval_samples_per_second": 860.571,
+      "eval_steps_per_second": 6.758,
+      "step": 400
+    },
+    {
+      "epoch": 1.4124293785310735,
+      "grad_norm": 0.16527259349822998,
+      "learning_rate": 0.0002576271186440678,
+      "loss": 0.0492,
+      "step": 500
+    },
+    {
+      "epoch": 1.694915254237288,
+      "grad_norm": 0.07748957723379135,
+      "learning_rate": 0.00024915254237288135,
+      "loss": 0.0518,
+      "step": 600
+    },
+    {
+      "epoch": 1.694915254237288,
+      "eval_accuracy": 0.9872763419483102,
+      "eval_f1": 0.9900482040118178,
+      "eval_loss": 0.04457252100110054,
+      "eval_precision": 0.9897404010570496,
+      "eval_recall": 0.9903561984756571,
+      "eval_runtime": 12.8001,
+      "eval_samples_per_second": 785.934,
+      "eval_steps_per_second": 6.172,
+      "step": 600
+    },
+    {
+      "epoch": 1.9774011299435028,
+      "grad_norm": 0.07877205312252045,
+      "learning_rate": 0.0002406779661016949,
+      "loss": 0.0489,
+      "step": 700
+    },
+    {
+      "epoch": 2.2598870056497176,
+      "grad_norm": 0.09426571428775787,
+      "learning_rate": 0.00023220338983050845,
+      "loss": 0.0477,
+      "step": 800
+    },
+    {
+      "epoch": 2.2598870056497176,
+      "eval_accuracy": 0.9879721669980119,
+      "eval_f1": 0.9906339499961297,
+      "eval_loss": 0.04242447018623352,
+      "eval_precision": 0.9859784283513097,
+      "eval_recall": 0.9953336444237051,
+      "eval_runtime": 13.2576,
+      "eval_samples_per_second": 758.811,
+      "eval_steps_per_second": 5.959,
+      "step": 800
+    },
+    {
+      "epoch": 2.542372881355932,
+      "grad_norm": 0.09674050658941269,
+      "learning_rate": 0.000223728813559322,
+      "loss": 0.0463,
+      "step": 900
+    },
+    {
+      "epoch": 2.824858757062147,
+      "grad_norm": 0.08737868070602417,
+      "learning_rate": 0.0002152542372881356,
+      "loss": 0.0465,
+      "step": 1000
+    },
+    {
+      "epoch": 2.824858757062147,
+      "eval_accuracy": 0.9887673956262425,
+      "eval_f1": 0.9912369135323769,
+      "eval_loss": 0.04115341976284981,
+      "eval_precision": 0.9884008660686668,
+      "eval_recall": 0.9940892829366931,
+      "eval_runtime": 11.8282,
+      "eval_samples_per_second": 850.507,
+      "eval_steps_per_second": 6.679,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3540,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8484875417960448.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7297b0ad9c787fcc96acb2d80cf44c24672bf5b6ed26aea98d5aa19bc46a5a78
+oid sha256:e00f8411aac819f03bb70d982baae4b32a1307eebb4ccf6268849efdf0d8bd88
 size 5048