Training in progress, epoch 2

tmp-checkpoint-4380/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa8dfd73098f82a3dec027052255349df935c2ded8f41261ee3350c67ceb52a
+size 995656250

tmp-checkpoint-4380/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a5c75c8b035d85260c13f7899ccb4ee06184934a866349e8c37fc43986d0ce
+size 14180

tmp-checkpoint-4380/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38672eacb6674d473013568eda9e8a1fa2eb4919d6f05bbf641c818f7740ab1e
+size 1064

tmp-checkpoint-4380/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "sep_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tmp-checkpoint-4380/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "sep_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

tmp-checkpoint-4380/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 1000000000,
+  "global_step": 4380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.680365296803653e-06,
+      "loss": 39.2485,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.354207436399217e-06,
+      "loss": 6.6145,
+      "step": 1000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.0280495759947813e-06,
+      "loss": 5.3605,
+      "step": 1500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.7018917155903456e-06,
+      "loss": 4.9587,
+      "step": 2000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.37573385518591e-06,
+      "loss": 4.7091,
+      "step": 2500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.0495759947814745e-06,
+      "loss": 4.4555,
+      "step": 3000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.7234181343770385e-06,
+      "loss": 4.2992,
+      "step": 3500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.3972602739726028e-06,
+      "loss": 4.2272,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6132,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 4577396584501248.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-4380/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a07cf7dc1b94a74872caec21a7cfe2d03c4c6da040f651bac83c8a18e944504
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87cabffd8af03d8c0e1b12514476e6f9b8fba7c9ed01a95b646f21edf1cdafc
-size 4664
+oid sha256:e7b77b2e343d5588f762dc72c81d8c8eb08569f3b051fc2d25ecc1c7fe776939
+size 4792