Training in progress, step 4272
Browse files- checkpoint-4272/config.json +39 -0
- checkpoint-4272/merges.txt +0 -0
- checkpoint-4272/optimizer.pt +3 -0
- checkpoint-4272/pytorch_model.bin +3 -0
- checkpoint-4272/rng_state.pth +3 -0
- checkpoint-4272/scaler.pt +3 -0
- checkpoint-4272/scheduler.pt +3 -0
- checkpoint-4272/special_tokens_map.json +6 -0
- checkpoint-4272/tokenizer.json +0 -0
- checkpoint-4272/tokenizer_config.json +10 -0
- checkpoint-4272/trainer_state.json +629 -0
- checkpoint-4272/training_args.bin +3 -0
- checkpoint-4272/vocab.json +0 -0
- config.json +39 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-4272/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMAndValueHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": true,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.23.0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
checkpoint-4272/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4272/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf05dd7d0b344d36c253cd9b885be329a2ddbc9ac8ec9a03283ee2109edb71cb
|
| 3 |
+
size 995605189
|
checkpoint-4272/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7f2c3cd966b8d4f41f06acfd1aa3a24e5bf5a658c4569bc8cc4a548714e4bbf
|
| 3 |
+
size 510398013
|
checkpoint-4272/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cff97b2022e48a3e529100fdac57bdeac6fc0e70705e3fde9626d13e1ae9f70d
|
| 3 |
+
size 15533
|
checkpoint-4272/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ccd8bf41083c6141a32843dc485ed4224977949db5caf03b089455b0293030f
|
| 3 |
+
size 557
|
checkpoint-4272/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01590ca3e35dffc28c40af0d7b715dc6b40f84ec790d82a115dbb8236f06d7e3
|
| 3 |
+
size 627
|
checkpoint-4272/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
checkpoint-4272/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4272/tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1024,
|
| 6 |
+
"name_or_path": "gpt2",
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
checkpoint-4272/trainer_state.json
ADDED
|
@@ -0,0 +1,629 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.09999063758075087,
|
| 5 |
+
"global_step": 4272,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 1.1682242990654204e-06,
|
| 13 |
+
"loss": 10.9364,
|
| 14 |
+
"theoretical_loss": 20.81281780154715,
|
| 15 |
+
"tokens_seen": 65536
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 5.841121495327103e-05,
|
| 20 |
+
"loss": 8.9947,
|
| 21 |
+
"theoretical_loss": 8.563482664611069,
|
| 22 |
+
"tokens_seen": 3276800
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.0,
|
| 26 |
+
"learning_rate": 0.00011682242990654206,
|
| 27 |
+
"loss": 7.0133,
|
| 28 |
+
"theoretical_loss": 7.4777587180480305,
|
| 29 |
+
"tokens_seen": 6553600
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.0,
|
| 33 |
+
"learning_rate": 0.00017523364485981307,
|
| 34 |
+
"loss": 6.2244,
|
| 35 |
+
"theoretical_loss": 6.9337544888949,
|
| 36 |
+
"tokens_seen": 9830400
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.0,
|
| 40 |
+
"learning_rate": 0.00023364485981308412,
|
| 41 |
+
"loss": 5.822,
|
| 42 |
+
"theoretical_loss": 6.583566228426414,
|
| 43 |
+
"tokens_seen": 13107200
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.01,
|
| 47 |
+
"learning_rate": 0.00029205607476635517,
|
| 48 |
+
"loss": 5.5642,
|
| 49 |
+
"theoretical_loss": 6.330713565116083,
|
| 50 |
+
"tokens_seen": 16384000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.01,
|
| 54 |
+
"learning_rate": 0.00035046728971962614,
|
| 55 |
+
"loss": 5.3688,
|
| 56 |
+
"theoretical_loss": 6.135529231940326,
|
| 57 |
+
"tokens_seen": 19660800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"learning_rate": 0.0004088785046728972,
|
| 62 |
+
"loss": 5.1987,
|
| 63 |
+
"theoretical_loss": 5.978101583869607,
|
| 64 |
+
"tokens_seen": 22937600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.01,
|
| 68 |
+
"learning_rate": 0.00046728971962616824,
|
| 69 |
+
"loss": 5.1026,
|
| 70 |
+
"theoretical_loss": 5.8471173262659235,
|
| 71 |
+
"tokens_seen": 26214400
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.01,
|
| 75 |
+
"learning_rate": 0.000499739928125591,
|
| 76 |
+
"loss": 4.9312,
|
| 77 |
+
"theoretical_loss": 5.7355768158821245,
|
| 78 |
+
"tokens_seen": 29491200
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.01,
|
| 82 |
+
"learning_rate": 0.0004991488556837526,
|
| 83 |
+
"loss": 4.8598,
|
| 84 |
+
"theoretical_loss": 5.638870144071353,
|
| 85 |
+
"tokens_seen": 32768000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.01,
|
| 89 |
+
"learning_rate": 0.0004985577832419141,
|
| 90 |
+
"loss": 4.7297,
|
| 91 |
+
"theoretical_loss": 5.553812381844907,
|
| 92 |
+
"tokens_seen": 36044800
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.01,
|
| 96 |
+
"learning_rate": 0.0004979667108000757,
|
| 97 |
+
"loss": 4.6466,
|
| 98 |
+
"theoretical_loss": 5.478118080556438,
|
| 99 |
+
"tokens_seen": 39321600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.02,
|
| 103 |
+
"learning_rate": 0.0004973756383582371,
|
| 104 |
+
"loss": 4.5646,
|
| 105 |
+
"theoretical_loss": 5.410095959579362,
|
| 106 |
+
"tokens_seen": 42598400
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.02,
|
| 110 |
+
"learning_rate": 0.0004967845659163987,
|
| 111 |
+
"loss": 4.5162,
|
| 112 |
+
"theoretical_loss": 5.348462083735834,
|
| 113 |
+
"tokens_seen": 45875200
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.02,
|
| 117 |
+
"learning_rate": 0.0004961934934745603,
|
| 118 |
+
"loss": 4.3809,
|
| 119 |
+
"theoretical_loss": 5.292220566937567,
|
| 120 |
+
"tokens_seen": 49152000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.02,
|
| 124 |
+
"learning_rate": 0.0004956024210327218,
|
| 125 |
+
"loss": 4.336,
|
| 126 |
+
"theoretical_loss": 5.240584625769978,
|
| 127 |
+
"tokens_seen": 52428800
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.02,
|
| 131 |
+
"learning_rate": 0.0004950113485908833,
|
| 132 |
+
"loss": 4.2829,
|
| 133 |
+
"theoretical_loss": 5.192922724525789,
|
| 134 |
+
"tokens_seen": 55705600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.02,
|
| 138 |
+
"learning_rate": 0.0004944202761490448,
|
| 139 |
+
"loss": 4.209,
|
| 140 |
+
"theoretical_loss": 5.1487208633564405,
|
| 141 |
+
"tokens_seen": 58982400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.02,
|
| 145 |
+
"learning_rate": 0.0004938292037072064,
|
| 146 |
+
"loss": 4.0751,
|
| 147 |
+
"theoretical_loss": 5.107555562405102,
|
| 148 |
+
"tokens_seen": 62259200
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.02,
|
| 152 |
+
"learning_rate": 0.0004932381312653678,
|
| 153 |
+
"loss": 3.9696,
|
| 154 |
+
"theoretical_loss": 5.069074117143246,
|
| 155 |
+
"tokens_seen": 65536000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.02,
|
| 159 |
+
"learning_rate": 0.0004926470588235294,
|
| 160 |
+
"loss": 3.9197,
|
| 161 |
+
"theoretical_loss": 5.032979909838007,
|
| 162 |
+
"tokens_seen": 68812800
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.03,
|
| 166 |
+
"learning_rate": 0.000492055986381691,
|
| 167 |
+
"loss": 3.8378,
|
| 168 |
+
"theoretical_loss": 4.999021308224664,
|
| 169 |
+
"tokens_seen": 72089600
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.03,
|
| 173 |
+
"learning_rate": 0.0004914649139398525,
|
| 174 |
+
"loss": 3.7856,
|
| 175 |
+
"theoretical_loss": 4.966983155351962,
|
| 176 |
+
"tokens_seen": 75366400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.03,
|
| 180 |
+
"learning_rate": 0.000490873841498014,
|
| 181 |
+
"loss": 3.6988,
|
| 182 |
+
"theoretical_loss": 4.9366801616251355,
|
| 183 |
+
"tokens_seen": 78643200
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.03,
|
| 187 |
+
"learning_rate": 0.0004902827690561755,
|
| 188 |
+
"loss": 3.6826,
|
| 189 |
+
"theoretical_loss": 4.907951713830082,
|
| 190 |
+
"tokens_seen": 81920000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.03,
|
| 194 |
+
"learning_rate": 0.0004896916966143371,
|
| 195 |
+
"loss": 3.6271,
|
| 196 |
+
"theoretical_loss": 4.880657753812926,
|
| 197 |
+
"tokens_seen": 85196800
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.03,
|
| 201 |
+
"learning_rate": 0.0004891006241724985,
|
| 202 |
+
"loss": 3.617,
|
| 203 |
+
"theoretical_loss": 4.854675474481779,
|
| 204 |
+
"tokens_seen": 88473600
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.03,
|
| 208 |
+
"learning_rate": 0.0004885095517306601,
|
| 209 |
+
"loss": 3.528,
|
| 210 |
+
"theoretical_loss": 4.8298966473088125,
|
| 211 |
+
"tokens_seen": 91750400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.03,
|
| 215 |
+
"learning_rate": 0.0004879184792888217,
|
| 216 |
+
"loss": 3.5513,
|
| 217 |
+
"theoretical_loss": 4.8062254427779205,
|
| 218 |
+
"tokens_seen": 95027200
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.04,
|
| 222 |
+
"learning_rate": 0.0004873274068469832,
|
| 223 |
+
"loss": 3.4962,
|
| 224 |
+
"theoretical_loss": 4.783576639276257,
|
| 225 |
+
"tokens_seen": 98304000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.04,
|
| 229 |
+
"learning_rate": 0.00048673633440514467,
|
| 230 |
+
"loss": 3.5334,
|
| 231 |
+
"theoretical_loss": 4.761874140772408,
|
| 232 |
+
"tokens_seen": 101580800
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.04,
|
| 236 |
+
"learning_rate": 0.0004861452619633062,
|
| 237 |
+
"loss": 3.5329,
|
| 238 |
+
"theoretical_loss": 4.741049741962473,
|
| 239 |
+
"tokens_seen": 104857600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.04,
|
| 243 |
+
"learning_rate": 0.0004855541895214677,
|
| 244 |
+
"loss": 3.5329,
|
| 245 |
+
"theoretical_loss": 4.721042093249051,
|
| 246 |
+
"tokens_seen": 108134400
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.04,
|
| 250 |
+
"learning_rate": 0.0004849631170796293,
|
| 251 |
+
"loss": 3.4926,
|
| 252 |
+
"theoretical_loss": 4.701795828231866,
|
| 253 |
+
"tokens_seen": 111411200
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.04,
|
| 257 |
+
"learning_rate": 0.0004843720446377908,
|
| 258 |
+
"loss": 3.4835,
|
| 259 |
+
"theoretical_loss": 4.68326082423593,
|
| 260 |
+
"tokens_seen": 114688000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.04,
|
| 264 |
+
"learning_rate": 0.00048378097219595233,
|
| 265 |
+
"loss": 3.4587,
|
| 266 |
+
"theoretical_loss": 4.665391572426282,
|
| 267 |
+
"tokens_seen": 117964800
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.04,
|
| 271 |
+
"learning_rate": 0.00048318989975411385,
|
| 272 |
+
"loss": 3.4307,
|
| 273 |
+
"theoretical_loss": 4.648146638719739,
|
| 274 |
+
"tokens_seen": 121241600
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.04,
|
| 278 |
+
"learning_rate": 0.00048259882731227537,
|
| 279 |
+
"loss": 3.443,
|
| 280 |
+
"theoretical_loss": 4.631488200339643,
|
| 281 |
+
"tokens_seen": 124518400
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.05,
|
| 285 |
+
"learning_rate": 0.0004820077548704369,
|
| 286 |
+
"loss": 3.45,
|
| 287 |
+
"theoretical_loss": 4.615381645715717,
|
| 288 |
+
"tokens_seen": 127795200
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.05,
|
| 292 |
+
"learning_rate": 0.00048141668242859847,
|
| 293 |
+
"loss": 3.3857,
|
| 294 |
+
"theoretical_loss": 4.599795227690505,
|
| 295 |
+
"tokens_seen": 131072000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.05,
|
| 299 |
+
"learning_rate": 0.00048082560998676,
|
| 300 |
+
"loss": 3.4065,
|
| 301 |
+
"theoretical_loss": 4.584699761792674,
|
| 302 |
+
"tokens_seen": 134348800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.05,
|
| 306 |
+
"learning_rate": 0.0004802345375449215,
|
| 307 |
+
"loss": 3.3659,
|
| 308 |
+
"theoretical_loss": 4.570068362778516,
|
| 309 |
+
"tokens_seen": 137625600
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.05,
|
| 313 |
+
"learning_rate": 0.00047964346510308303,
|
| 314 |
+
"loss": 3.3781,
|
| 315 |
+
"theoretical_loss": 4.555876213804037,
|
| 316 |
+
"tokens_seen": 140902400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.05,
|
| 320 |
+
"learning_rate": 0.00047905239266124455,
|
| 321 |
+
"loss": 3.3612,
|
| 322 |
+
"theoretical_loss": 4.542100363530799,
|
| 323 |
+
"tokens_seen": 144179200
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.05,
|
| 327 |
+
"learning_rate": 0.00047846132021940607,
|
| 328 |
+
"loss": 3.3402,
|
| 329 |
+
"theoretical_loss": 4.528719547234816,
|
| 330 |
+
"tokens_seen": 147456000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.05,
|
| 334 |
+
"learning_rate": 0.0004778702477775676,
|
| 335 |
+
"loss": 3.2899,
|
| 336 |
+
"theoretical_loss": 4.515714028614996,
|
| 337 |
+
"tokens_seen": 150732800
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.06,
|
| 341 |
+
"learning_rate": 0.00047727917533572917,
|
| 342 |
+
"loss": 3.3099,
|
| 343 |
+
"theoretical_loss": 4.503065459513339,
|
| 344 |
+
"tokens_seen": 154009600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.06,
|
| 348 |
+
"learning_rate": 0.0004766881028938907,
|
| 349 |
+
"loss": 3.3162,
|
| 350 |
+
"theoretical_loss": 4.4907567551852665,
|
| 351 |
+
"tokens_seen": 157286400
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.06,
|
| 355 |
+
"learning_rate": 0.0004760970304520522,
|
| 356 |
+
"loss": 3.3036,
|
| 357 |
+
"theoretical_loss": 4.478771983111967,
|
| 358 |
+
"tokens_seen": 160563200
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.06,
|
| 362 |
+
"objective/train/docs_used": 104000,
|
| 363 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 364 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 365 |
+
"objective/train/original_loss": 3.2747654914855957,
|
| 366 |
+
"objective/train/theoretical_loss": 4.467096263641219,
|
| 367 |
+
"objective/train/tokens_used": 184300000,
|
| 368 |
+
"theoretical_loss": 4.467096263641219,
|
| 369 |
+
"tokens_seen": 163840000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.06,
|
| 373 |
+
"learning_rate": 0.00047550595801021373,
|
| 374 |
+
"loss": 3.2837,
|
| 375 |
+
"theoretical_loss": 4.467096263641219,
|
| 376 |
+
"tokens_seen": 163840000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.06,
|
| 380 |
+
"learning_rate": 0.00047491488556837525,
|
| 381 |
+
"loss": 3.2955,
|
| 382 |
+
"theoretical_loss": 4.455715680989545,
|
| 383 |
+
"tokens_seen": 167116800
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.06,
|
| 387 |
+
"learning_rate": 0.00047432381312653677,
|
| 388 |
+
"loss": 3.2608,
|
| 389 |
+
"theoretical_loss": 4.44461720334543,
|
| 390 |
+
"tokens_seen": 170393600
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.06,
|
| 394 |
+
"learning_rate": 0.00047373274068469835,
|
| 395 |
+
"loss": 3.2026,
|
| 396 |
+
"theoretical_loss": 4.433788610987646,
|
| 397 |
+
"tokens_seen": 173670400
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.06,
|
| 401 |
+
"learning_rate": 0.00047314166824285987,
|
| 402 |
+
"loss": 3.2621,
|
| 403 |
+
"theoretical_loss": 4.42321843148016,
|
| 404 |
+
"tokens_seen": 176947200
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.06,
|
| 408 |
+
"learning_rate": 0.0004725505958010214,
|
| 409 |
+
"loss": 3.1999,
|
| 410 |
+
"theoretical_loss": 4.412895881130142,
|
| 411 |
+
"tokens_seen": 180224000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.07,
|
| 415 |
+
"learning_rate": 0.0004719595233591829,
|
| 416 |
+
"loss": 3.2384,
|
| 417 |
+
"theoretical_loss": 4.4028108120020795,
|
| 418 |
+
"tokens_seen": 183500800
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.07,
|
| 422 |
+
"learning_rate": 0.00047136845091734443,
|
| 423 |
+
"loss": 3.244,
|
| 424 |
+
"theoretical_loss": 4.392953663871862,
|
| 425 |
+
"tokens_seen": 186777600
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.07,
|
| 429 |
+
"learning_rate": 0.00047077737847550595,
|
| 430 |
+
"loss": 3.2329,
|
| 431 |
+
"theoretical_loss": 4.383315420582533,
|
| 432 |
+
"tokens_seen": 190054400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.07,
|
| 436 |
+
"learning_rate": 0.0004701863060336675,
|
| 437 |
+
"loss": 3.2634,
|
| 438 |
+
"theoretical_loss": 4.373887570330275,
|
| 439 |
+
"tokens_seen": 193331200
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.07,
|
| 443 |
+
"learning_rate": 0.00046959523359182905,
|
| 444 |
+
"loss": 3.2143,
|
| 445 |
+
"theoretical_loss": 4.364662069466704,
|
| 446 |
+
"tokens_seen": 196608000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.07,
|
| 450 |
+
"learning_rate": 0.00046900416114999057,
|
| 451 |
+
"loss": 3.2128,
|
| 452 |
+
"theoretical_loss": 4.355631309453283,
|
| 453 |
+
"tokens_seen": 199884800
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.07,
|
| 457 |
+
"learning_rate": 0.0004684130887081521,
|
| 458 |
+
"loss": 3.1675,
|
| 459 |
+
"theoretical_loss": 4.346788086646671,
|
| 460 |
+
"tokens_seen": 203161600
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.07,
|
| 464 |
+
"learning_rate": 0.0004678220162663136,
|
| 465 |
+
"loss": 3.1967,
|
| 466 |
+
"theoretical_loss": 4.33812557463116,
|
| 467 |
+
"tokens_seen": 206438400
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.07,
|
| 471 |
+
"learning_rate": 0.00046723094382447513,
|
| 472 |
+
"loss": 3.2042,
|
| 473 |
+
"theoretical_loss": 4.329637298846812,
|
| 474 |
+
"tokens_seen": 209715200
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.08,
|
| 478 |
+
"learning_rate": 0.00046663987138263665,
|
| 479 |
+
"loss": 3.1574,
|
| 480 |
+
"theoretical_loss": 4.321317113290252,
|
| 481 |
+
"tokens_seen": 212992000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.08,
|
| 485 |
+
"learning_rate": 0.0004660487989407982,
|
| 486 |
+
"loss": 3.1317,
|
| 487 |
+
"theoretical_loss": 4.3131591790897925,
|
| 488 |
+
"tokens_seen": 216268800
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.08,
|
| 492 |
+
"learning_rate": 0.00046545772649895975,
|
| 493 |
+
"loss": 3.1829,
|
| 494 |
+
"theoretical_loss": 4.305157944778228,
|
| 495 |
+
"tokens_seen": 219545600
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.08,
|
| 499 |
+
"learning_rate": 0.00046486665405712127,
|
| 500 |
+
"loss": 3.2073,
|
| 501 |
+
"theoretical_loss": 4.297308128105687,
|
| 502 |
+
"tokens_seen": 222822400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.08,
|
| 506 |
+
"learning_rate": 0.0004642755816152828,
|
| 507 |
+
"loss": 3.1994,
|
| 508 |
+
"theoretical_loss": 4.2896046992515995,
|
| 509 |
+
"tokens_seen": 226099200
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.08,
|
| 513 |
+
"learning_rate": 0.0004636845091734443,
|
| 514 |
+
"loss": 3.2312,
|
| 515 |
+
"theoretical_loss": 4.282042865309616,
|
| 516 |
+
"tokens_seen": 229376000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.08,
|
| 520 |
+
"learning_rate": 0.00046309343673160583,
|
| 521 |
+
"loss": 3.2006,
|
| 522 |
+
"theoretical_loss": 4.274618055932298,
|
| 523 |
+
"tokens_seen": 232652800
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.08,
|
| 527 |
+
"learning_rate": 0.0004625023642897674,
|
| 528 |
+
"loss": 3.1756,
|
| 529 |
+
"theoretical_loss": 4.267325910033897,
|
| 530 |
+
"tokens_seen": 235929600
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.09,
|
| 534 |
+
"learning_rate": 0.0004619112918479289,
|
| 535 |
+
"loss": 3.1158,
|
| 536 |
+
"theoretical_loss": 4.260162263459744,
|
| 537 |
+
"tokens_seen": 239206400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.09,
|
| 541 |
+
"learning_rate": 0.00046132021940609044,
|
| 542 |
+
"loss": 3.1448,
|
| 543 |
+
"theoretical_loss": 4.253123137539814,
|
| 544 |
+
"tokens_seen": 242483200
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.09,
|
| 548 |
+
"learning_rate": 0.00046072914696425197,
|
| 549 |
+
"loss": 3.166,
|
| 550 |
+
"theoretical_loss": 4.246204728452055,
|
| 551 |
+
"tokens_seen": 245760000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.09,
|
| 555 |
+
"learning_rate": 0.0004601380745224135,
|
| 556 |
+
"loss": 3.1762,
|
| 557 |
+
"theoretical_loss": 4.239403397328261,
|
| 558 |
+
"tokens_seen": 249036800
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.09,
|
| 562 |
+
"learning_rate": 0.000459547002080575,
|
| 563 |
+
"loss": 3.1442,
|
| 564 |
+
"theoretical_loss": 4.232715661041632,
|
| 565 |
+
"tokens_seen": 252313600
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.09,
|
| 569 |
+
"learning_rate": 0.0004589559296387366,
|
| 570 |
+
"loss": 3.1504,
|
| 571 |
+
"theoretical_loss": 4.226138183620867,
|
| 572 |
+
"tokens_seen": 255590400
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.09,
|
| 576 |
+
"learning_rate": 0.0004583648571968981,
|
| 577 |
+
"loss": 3.1099,
|
| 578 |
+
"theoretical_loss": 4.219667768240775,
|
| 579 |
+
"tokens_seen": 258867200
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.09,
|
| 583 |
+
"learning_rate": 0.0004577737847550596,
|
| 584 |
+
"loss": 3.114,
|
| 585 |
+
"theoretical_loss": 4.213301349743924,
|
| 586 |
+
"tokens_seen": 262144000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.09,
|
| 590 |
+
"learning_rate": 0.0004571827123132211,
|
| 591 |
+
"loss": 3.0703,
|
| 592 |
+
"theoretical_loss": 4.20703598765197,
|
| 593 |
+
"tokens_seen": 265420800
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.1,
|
| 597 |
+
"learning_rate": 0.0004565916398713826,
|
| 598 |
+
"loss": 3.0383,
|
| 599 |
+
"theoretical_loss": 4.2008688596290025,
|
| 600 |
+
"tokens_seen": 268697600
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.1,
|
| 604 |
+
"learning_rate": 0.00045600056742954413,
|
| 605 |
+
"loss": 2.9881,
|
| 606 |
+
"theoretical_loss": 4.194797255362549,
|
| 607 |
+
"tokens_seen": 271974400
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.1,
|
| 611 |
+
"learning_rate": 0.0004554094949877057,
|
| 612 |
+
"loss": 3.068,
|
| 613 |
+
"theoretical_loss": 4.188818570830883,
|
| 614 |
+
"tokens_seen": 275251200
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.1,
|
| 618 |
+
"learning_rate": 0.00045481842254586723,
|
| 619 |
+
"loss": 3.0823,
|
| 620 |
+
"theoretical_loss": 4.182930302927963,
|
| 621 |
+
"tokens_seen": 278528000
|
| 622 |
+
}
|
| 623 |
+
],
|
| 624 |
+
"max_steps": 42724,
|
| 625 |
+
"num_train_epochs": 9223372036854775807,
|
| 626 |
+
"total_flos": 1.42878663770112e+17,
|
| 627 |
+
"trial_name": null,
|
| 628 |
+
"trial_params": null
|
| 629 |
+
}
|
checkpoint-4272/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b99f0235a96529e0f83ff582cf9a79155af5321a32b48f56f5aaa8415957f796
|
| 3 |
+
size 3451
|
checkpoint-4272/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMAndValueHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": true,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.23.0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7f2c3cd966b8d4f41f06acfd1aa3a24e5bf5a658c4569bc8cc4a548714e4bbf
|
| 3 |
+
size 510398013
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1024,
|
| 6 |
+
"name_or_path": "gpt2",
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b99f0235a96529e0f83ff582cf9a79155af5321a32b48f56f5aaa8415957f796
|
| 3 |
+
size 3451
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|