add all josn

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 0.02,
+    "eval_loss": 1.4698705673217773,
+    "eval_runtime": 294.5013,
+    "eval_samples_per_second": 3.396,
+    "eval_steps_per_second": 0.849,
+    "train_loss": 1.198510036468506,
+    "train_runtime": 688.023,
+    "train_samples_per_second": 1.163,
+    "train_steps_per_second": 0.073
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.02,
+    "eval_loss": 1.4698705673217773,
+    "eval_runtime": 294.5013,
+    "eval_samples_per_second": 3.396,
+    "eval_steps_per_second": 0.849
+}

metrics.json

@@ -0,0 +1 @@
+{"run_name": "./output3", "train_runtime": 688.023, "train_samples_per_second": 1.163, "train_steps_per_second": 0.073, "train_loss": 1.198510036468506, "epoch": 0.02, "eval_loss": 1.4698705673217773, "eval_runtime": 294.5013, "eval_samples_per_second": 3.396, "eval_steps_per_second": 0.849}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.02,
+    "train_loss": 1.198510036468506,
+    "train_runtime": 688.023,
+    "train_samples_per_second": 1.163,
+    "train_steps_per_second": 0.073
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.01569242840329541,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 1.4673,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.2893,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.1835,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.0317,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002,
+      "loss": 1.0207,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "step": 50,
+      "total_flos": 2292376788271104.0,
+      "train_loss": 1.198510036468506,
+      "train_runtime": 688.023,
+      "train_samples_per_second": 1.163,
+      "train_steps_per_second": 0.073
+    }
+  ],
+  "max_steps": 50,
+  "num_train_epochs": 1,
+  "total_flos": 2292376788271104.0,
+  "trial_name": null,
+  "trial_params": null
+}