Training in progress, step 5

checkpoint-5/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "codeparrot/codeparrot-small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMAndValueHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

checkpoint-5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccfd80df3433f994885fcf35b8dfcad70c6b25b456287dd2b0da79f32e8043
+size 888151409

checkpoint-5/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610dbb2ae7b16c215d8d70480eaaed465876cbd36bf24aca0ff438e328d92413
+size 456678185

checkpoint-5/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd24ac692aa66db8bced3fd1c33ca3b87d4aafb2ed528c2296bfe9a2f8ec9e4
+size 14503

checkpoint-5/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c790dad68f84cf6548b6f8763332f882ce5014368cea34055202446c39a4958
+size 559

checkpoint-5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c82ab0ab95f5e11168d9c0b13c9304074d960263b1ea5ef74b4922616247fd
+size 623

checkpoint-5/special_tokens_map.json

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

checkpoint-5/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "codeparrot/codeparrot-small", "tokenizer_class": "GPT2Tokenizer"}

checkpoint-5/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3333333333333333,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0005,
+      "loss": 10.5545,
+      "theoretical_loss": 20.841284642178216,
+      "tokens_seen": 65536
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00046428571428571433,
+      "loss": 10.5833,
+      "theoretical_loss": 17.59466794495971,
+      "tokens_seen": 131072
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00042857142857142855,
+      "loss": 9.0487,
+      "theoretical_loss": 15.967943933467634,
+      "tokens_seen": 196608
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003928571428571429,
+      "loss": 8.6045,
+      "theoretical_loss": 14.920783596619636,
+      "tokens_seen": 262144
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00035714285714285714,
+      "loss": 8.612,
+      "theoretical_loss": 14.164683778394041,
+      "tokens_seen": 327680
+    }
+  ],
+  "max_steps": 15,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 167226900480000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a34744d720995e937e6f88654fd722891f574db162e25b56a6b9fa429b1c293
+size 3055

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a251f33e7271e8dc2f8313d2aa9ac00ff941ded6b800cc767cab402590dd7153
+oid sha256:610dbb2ae7b16c215d8d70480eaaed465876cbd36bf24aca0ff438e328d92413
 size 456678185

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d1e83c3ca51308f5ebb0f10ae5ffaf864dd4254cf5bd9d3ff7bdd866102c0d
+oid sha256:5a34744d720995e937e6f88654fd722891f574db162e25b56a6b9fa429b1c293
 size 3055