Training in progress, step 1000, checkpoint
Browse files- checkpoint-1000/config.json +184 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state_0.pth +3 -0
- checkpoint-1000/rng_state_1.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +737 -0
- checkpoint-1000/training_args.bin +3 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"K": 4096,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MomentumDualEncoderModel"
|
| 5 |
+
],
|
| 6 |
+
"assembly_config": {
|
| 7 |
+
"_name_or_path": "",
|
| 8 |
+
"add_cross_attention": false,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"LongelmForMaskedLMWithEdgePrediction"
|
| 11 |
+
],
|
| 12 |
+
"attention_probs_dropout_prob": 0.1,
|
| 13 |
+
"bad_words_ids": null,
|
| 14 |
+
"begin_suppress_tokens": null,
|
| 15 |
+
"block_size": 8,
|
| 16 |
+
"bos_token_id": 1,
|
| 17 |
+
"chunk_size_feed_forward": 0,
|
| 18 |
+
"classifier_dropout": null,
|
| 19 |
+
"cross_attention_hidden_size": null,
|
| 20 |
+
"decoder_start_token_id": null,
|
| 21 |
+
"diversity_penalty": 0.0,
|
| 22 |
+
"do_sample": false,
|
| 23 |
+
"early_stopping": false,
|
| 24 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 25 |
+
"eos_token_id": 2,
|
| 26 |
+
"ep_add_linear_projection": true,
|
| 27 |
+
"exponential_decay_length_penalty": null,
|
| 28 |
+
"finetuning_task": null,
|
| 29 |
+
"forced_bos_token_id": null,
|
| 30 |
+
"forced_eos_token_id": null,
|
| 31 |
+
"global_memory_size": 1,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-12,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_blocks": 200,
|
| 50 |
+
"max_length": 20,
|
| 51 |
+
"max_position_embeddings": 1805,
|
| 52 |
+
"max_relative_position_embeddings": 8,
|
| 53 |
+
"min_length": 0,
|
| 54 |
+
"model_type": "longelm",
|
| 55 |
+
"no_repeat_ngram_size": 0,
|
| 56 |
+
"node_size": 1,
|
| 57 |
+
"num_attention_heads": 12,
|
| 58 |
+
"num_beam_groups": 1,
|
| 59 |
+
"num_beams": 1,
|
| 60 |
+
"num_hidden_layers": 12,
|
| 61 |
+
"num_return_sequences": 1,
|
| 62 |
+
"output_attentions": false,
|
| 63 |
+
"output_hidden_states": false,
|
| 64 |
+
"output_scores": false,
|
| 65 |
+
"pad_token_id": 3,
|
| 66 |
+
"position_embedding_type": "mixed",
|
| 67 |
+
"prefix": null,
|
| 68 |
+
"problem_type": null,
|
| 69 |
+
"pruned_heads": {},
|
| 70 |
+
"remove_invalid_values": false,
|
| 71 |
+
"repetition_penalty": 1.0,
|
| 72 |
+
"return_dict": true,
|
| 73 |
+
"return_dict_in_generate": false,
|
| 74 |
+
"sep_token_id": null,
|
| 75 |
+
"suppress_tokens": null,
|
| 76 |
+
"task_specific_params": null,
|
| 77 |
+
"temperature": 1.0,
|
| 78 |
+
"tf_legacy_loss": false,
|
| 79 |
+
"tie_encoder_decoder": false,
|
| 80 |
+
"tie_word_embeddings": true,
|
| 81 |
+
"tokenizer_class": null,
|
| 82 |
+
"top_k": 50,
|
| 83 |
+
"top_p": 1.0,
|
| 84 |
+
"torch_dtype": "float32",
|
| 85 |
+
"torchscript": false,
|
| 86 |
+
"type_vocab_size": 2,
|
| 87 |
+
"typical_p": 1.0,
|
| 88 |
+
"use_bfloat16": false,
|
| 89 |
+
"use_cache": true,
|
| 90 |
+
"vocab_size": 50265
|
| 91 |
+
},
|
| 92 |
+
"logit_scale_init_value": 2.6592,
|
| 93 |
+
"m": 0.999,
|
| 94 |
+
"model_type": "assembly-source-dual-encoder",
|
| 95 |
+
"projection_dim": 512,
|
| 96 |
+
"source_config": {
|
| 97 |
+
"_name_or_path": "Salesforce/codet5p-110m-embedding",
|
| 98 |
+
"add_cross_attention": false,
|
| 99 |
+
"architectures": [
|
| 100 |
+
"CodeT5p_Embedding"
|
| 101 |
+
],
|
| 102 |
+
"auto_map": {
|
| 103 |
+
"AutoConfig": "Salesforce/codet5p-110m-embedding--configuration_codet5p_embedding.CodeT5pEmbeddingConfig",
|
| 104 |
+
"AutoModel": "Salesforce/codet5p-110m-embedding--modeling_codet5p_embedding.CodeT5pEmbeddingModel"
|
| 105 |
+
},
|
| 106 |
+
"bad_words_ids": null,
|
| 107 |
+
"begin_suppress_tokens": null,
|
| 108 |
+
"bos_token_id": 1,
|
| 109 |
+
"chunk_size_feed_forward": 0,
|
| 110 |
+
"cross_attention_hidden_size": null,
|
| 111 |
+
"d_ff": 3072,
|
| 112 |
+
"d_kv": 64,
|
| 113 |
+
"d_model": 768,
|
| 114 |
+
"decoder_start_token_id": 0,
|
| 115 |
+
"dense_act_fn": "relu",
|
| 116 |
+
"diversity_penalty": 0.0,
|
| 117 |
+
"do_sample": false,
|
| 118 |
+
"dropout_rate": 0.1,
|
| 119 |
+
"early_stopping": false,
|
| 120 |
+
"embed_dim": 256,
|
| 121 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 122 |
+
"eos_token_id": 2,
|
| 123 |
+
"exponential_decay_length_penalty": null,
|
| 124 |
+
"feed_forward_proj": "relu",
|
| 125 |
+
"finetuning_task": null,
|
| 126 |
+
"forced_bos_token_id": null,
|
| 127 |
+
"forced_eos_token_id": null,
|
| 128 |
+
"gradient_checkpointing": false,
|
| 129 |
+
"id2label": {
|
| 130 |
+
"0": "LABEL_0"
|
| 131 |
+
},
|
| 132 |
+
"initializer_factor": 1.0,
|
| 133 |
+
"is_decoder": false,
|
| 134 |
+
"is_encoder_decoder": true,
|
| 135 |
+
"is_gated_act": false,
|
| 136 |
+
"label2id": {
|
| 137 |
+
"LABEL_0": 0
|
| 138 |
+
},
|
| 139 |
+
"layer_norm_epsilon": 1e-06,
|
| 140 |
+
"length_penalty": 1.0,
|
| 141 |
+
"max_length": 20,
|
| 142 |
+
"min_length": 0,
|
| 143 |
+
"model_type": "codet5p_embedding",
|
| 144 |
+
"n_positions": 512,
|
| 145 |
+
"no_repeat_ngram_size": 0,
|
| 146 |
+
"num_beam_groups": 1,
|
| 147 |
+
"num_beams": 1,
|
| 148 |
+
"num_heads": 12,
|
| 149 |
+
"num_layers": 12,
|
| 150 |
+
"num_return_sequences": 1,
|
| 151 |
+
"output_attentions": false,
|
| 152 |
+
"output_hidden_states": false,
|
| 153 |
+
"output_past": true,
|
| 154 |
+
"output_scores": false,
|
| 155 |
+
"pad_token_id": 0,
|
| 156 |
+
"prefix": null,
|
| 157 |
+
"problem_type": null,
|
| 158 |
+
"pruned_heads": {},
|
| 159 |
+
"relative_attention_max_distance": 128,
|
| 160 |
+
"relative_attention_num_buckets": 32,
|
| 161 |
+
"remove_invalid_values": false,
|
| 162 |
+
"repetition_penalty": 1.0,
|
| 163 |
+
"return_dict": true,
|
| 164 |
+
"return_dict_in_generate": false,
|
| 165 |
+
"sep_token_id": null,
|
| 166 |
+
"suppress_tokens": null,
|
| 167 |
+
"task_specific_params": null,
|
| 168 |
+
"temperature": 1.0,
|
| 169 |
+
"tf_legacy_loss": false,
|
| 170 |
+
"tie_encoder_decoder": false,
|
| 171 |
+
"tie_word_embeddings": true,
|
| 172 |
+
"tokenizer_class": null,
|
| 173 |
+
"top_k": 50,
|
| 174 |
+
"top_p": 1.0,
|
| 175 |
+
"torch_dtype": "float32",
|
| 176 |
+
"torchscript": false,
|
| 177 |
+
"typical_p": 1.0,
|
| 178 |
+
"use_bfloat16": false,
|
| 179 |
+
"use_cache": false,
|
| 180 |
+
"vocab_size": 32103
|
| 181 |
+
},
|
| 182 |
+
"torch_dtype": "float32",
|
| 183 |
+
"transformers_version": "4.39.3"
|
| 184 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46650cbb24f2f28bc0f8d4e63dbe1cd79075af9517240fbf3043bb153ba58e6b
|
| 3 |
+
size 1901991436
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3b53575b56aaf4d5d3c285b5283aeca59163caefaffd44269f69f6aab56ebb4
|
| 3 |
+
size 1888540293
|
checkpoint-1000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34340f25d48027ca7202524a47804e1f5d9684c13b399c5df592f17ef4ca3bd
|
| 3 |
+
size 15607
|
checkpoint-1000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07a51ce09d2f8940034903318fadffdd3d27f975d4fdfe12888cc28efbf82446
|
| 3 |
+
size 15607
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b4edceaa965fcfb2df8dfb454d9e0d07beee3e0f9d014eb01baa1522389dfa4
|
| 3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,737 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03968253968253968,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 23.495065689086914,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 8.6232,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0,
|
| 20 |
+
"grad_norm": 24.87381935119629,
|
| 21 |
+
"learning_rate": 9e-07,
|
| 22 |
+
"loss": 8.4514,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0,
|
| 27 |
+
"grad_norm": 22.63846778869629,
|
| 28 |
+
"learning_rate": 1.4000000000000001e-06,
|
| 29 |
+
"loss": 8.3152,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0,
|
| 34 |
+
"grad_norm": 20.65507698059082,
|
| 35 |
+
"learning_rate": 1.9e-06,
|
| 36 |
+
"loss": 7.9732,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0,
|
| 41 |
+
"grad_norm": 16.147356033325195,
|
| 42 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 43 |
+
"loss": 7.6879,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0,
|
| 48 |
+
"grad_norm": 14.252687454223633,
|
| 49 |
+
"learning_rate": 2.9e-06,
|
| 50 |
+
"loss": 7.4152,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0,
|
| 55 |
+
"grad_norm": 12.011382102966309,
|
| 56 |
+
"learning_rate": 3.4000000000000005e-06,
|
| 57 |
+
"loss": 7.2472,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0,
|
| 62 |
+
"grad_norm": 10.081536293029785,
|
| 63 |
+
"learning_rate": 3.9e-06,
|
| 64 |
+
"loss": 7.2433,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0,
|
| 69 |
+
"grad_norm": 9.65556526184082,
|
| 70 |
+
"learning_rate": 4.4e-06,
|
| 71 |
+
"loss": 7.2298,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0,
|
| 76 |
+
"grad_norm": 8.830799102783203,
|
| 77 |
+
"learning_rate": 4.9000000000000005e-06,
|
| 78 |
+
"loss": 7.19,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0,
|
| 83 |
+
"grad_norm": 9.019427299499512,
|
| 84 |
+
"learning_rate": 5.4e-06,
|
| 85 |
+
"loss": 7.2362,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0,
|
| 90 |
+
"grad_norm": 9.13768482208252,
|
| 91 |
+
"learning_rate": 5.9e-06,
|
| 92 |
+
"loss": 7.2804,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.01,
|
| 97 |
+
"grad_norm": 9.02840805053711,
|
| 98 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 99 |
+
"loss": 7.2345,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.01,
|
| 104 |
+
"grad_norm": 8.178731918334961,
|
| 105 |
+
"learning_rate": 6.900000000000001e-06,
|
| 106 |
+
"loss": 7.3014,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.01,
|
| 111 |
+
"grad_norm": 8.83882999420166,
|
| 112 |
+
"learning_rate": 7.4e-06,
|
| 113 |
+
"loss": 7.3875,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.01,
|
| 118 |
+
"grad_norm": 8.3687162399292,
|
| 119 |
+
"learning_rate": 7.9e-06,
|
| 120 |
+
"loss": 7.4546,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.01,
|
| 125 |
+
"grad_norm": 8.09121036529541,
|
| 126 |
+
"learning_rate": 8.400000000000001e-06,
|
| 127 |
+
"loss": 7.407,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.01,
|
| 132 |
+
"grad_norm": 12.731450080871582,
|
| 133 |
+
"learning_rate": 8.9e-06,
|
| 134 |
+
"loss": 7.4321,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.01,
|
| 139 |
+
"grad_norm": 7.601162910461426,
|
| 140 |
+
"learning_rate": 9.4e-06,
|
| 141 |
+
"loss": 7.4155,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.01,
|
| 146 |
+
"grad_norm": 8.006213188171387,
|
| 147 |
+
"learning_rate": 9.900000000000002e-06,
|
| 148 |
+
"loss": 7.3705,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.01,
|
| 153 |
+
"grad_norm": 7.79794454574585,
|
| 154 |
+
"learning_rate": 1.04e-05,
|
| 155 |
+
"loss": 7.3759,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.01,
|
| 160 |
+
"grad_norm": 7.281346321105957,
|
| 161 |
+
"learning_rate": 1.09e-05,
|
| 162 |
+
"loss": 7.3798,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.01,
|
| 167 |
+
"grad_norm": 7.605266094207764,
|
| 168 |
+
"learning_rate": 1.1400000000000001e-05,
|
| 169 |
+
"loss": 7.3878,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.01,
|
| 174 |
+
"grad_norm": 7.446412563323975,
|
| 175 |
+
"learning_rate": 1.19e-05,
|
| 176 |
+
"loss": 7.3098,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.01,
|
| 181 |
+
"grad_norm": 7.6324334144592285,
|
| 182 |
+
"learning_rate": 1.24e-05,
|
| 183 |
+
"loss": 7.2995,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.01,
|
| 188 |
+
"grad_norm": 8.330737113952637,
|
| 189 |
+
"learning_rate": 1.29e-05,
|
| 190 |
+
"loss": 7.1887,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.01,
|
| 195 |
+
"grad_norm": 7.283708572387695,
|
| 196 |
+
"learning_rate": 1.3400000000000002e-05,
|
| 197 |
+
"loss": 7.1184,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.01,
|
| 202 |
+
"grad_norm": 6.950069904327393,
|
| 203 |
+
"learning_rate": 1.3900000000000002e-05,
|
| 204 |
+
"loss": 6.9876,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.01,
|
| 209 |
+
"grad_norm": 6.844958782196045,
|
| 210 |
+
"learning_rate": 1.44e-05,
|
| 211 |
+
"loss": 6.9319,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.01,
|
| 216 |
+
"grad_norm": 7.499362468719482,
|
| 217 |
+
"learning_rate": 1.49e-05,
|
| 218 |
+
"loss": 6.9253,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.01,
|
| 223 |
+
"grad_norm": 8.45572280883789,
|
| 224 |
+
"learning_rate": 1.54e-05,
|
| 225 |
+
"loss": 6.7999,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.01,
|
| 230 |
+
"grad_norm": 8.108625411987305,
|
| 231 |
+
"learning_rate": 1.59e-05,
|
| 232 |
+
"loss": 6.7667,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.01,
|
| 237 |
+
"grad_norm": 8.131596565246582,
|
| 238 |
+
"learning_rate": 1.6400000000000002e-05,
|
| 239 |
+
"loss": 6.7599,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.01,
|
| 244 |
+
"grad_norm": 7.2159247398376465,
|
| 245 |
+
"learning_rate": 1.69e-05,
|
| 246 |
+
"loss": 6.7379,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.01,
|
| 251 |
+
"grad_norm": 7.335048675537109,
|
| 252 |
+
"learning_rate": 1.74e-05,
|
| 253 |
+
"loss": 6.6553,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.01,
|
| 258 |
+
"grad_norm": 7.361081600189209,
|
| 259 |
+
"learning_rate": 1.79e-05,
|
| 260 |
+
"loss": 6.6905,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.01,
|
| 265 |
+
"grad_norm": 7.59442138671875,
|
| 266 |
+
"learning_rate": 1.84e-05,
|
| 267 |
+
"loss": 6.6356,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.02,
|
| 272 |
+
"grad_norm": 7.31695032119751,
|
| 273 |
+
"learning_rate": 1.8900000000000002e-05,
|
| 274 |
+
"loss": 6.6538,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.02,
|
| 279 |
+
"grad_norm": 7.541380882263184,
|
| 280 |
+
"learning_rate": 1.94e-05,
|
| 281 |
+
"loss": 6.6873,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.02,
|
| 286 |
+
"grad_norm": 8.056180000305176,
|
| 287 |
+
"learning_rate": 1.9900000000000003e-05,
|
| 288 |
+
"loss": 6.6332,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.02,
|
| 293 |
+
"grad_norm": 6.74859094619751,
|
| 294 |
+
"learning_rate": 2.04e-05,
|
| 295 |
+
"loss": 6.5488,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.02,
|
| 300 |
+
"grad_norm": 7.700525760650635,
|
| 301 |
+
"learning_rate": 2.09e-05,
|
| 302 |
+
"loss": 6.611,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.02,
|
| 307 |
+
"grad_norm": 7.347009181976318,
|
| 308 |
+
"learning_rate": 2.1400000000000002e-05,
|
| 309 |
+
"loss": 6.6621,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.02,
|
| 314 |
+
"grad_norm": 6.607337951660156,
|
| 315 |
+
"learning_rate": 2.19e-05,
|
| 316 |
+
"loss": 6.568,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.02,
|
| 321 |
+
"grad_norm": 6.816825866699219,
|
| 322 |
+
"learning_rate": 2.2400000000000002e-05,
|
| 323 |
+
"loss": 6.6293,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.02,
|
| 328 |
+
"grad_norm": 6.984443664550781,
|
| 329 |
+
"learning_rate": 2.29e-05,
|
| 330 |
+
"loss": 6.5667,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.02,
|
| 335 |
+
"grad_norm": 6.995021820068359,
|
| 336 |
+
"learning_rate": 2.3400000000000003e-05,
|
| 337 |
+
"loss": 6.5062,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.02,
|
| 342 |
+
"grad_norm": 6.876286029815674,
|
| 343 |
+
"learning_rate": 2.39e-05,
|
| 344 |
+
"loss": 6.5034,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.02,
|
| 349 |
+
"grad_norm": 6.953365802764893,
|
| 350 |
+
"learning_rate": 2.44e-05,
|
| 351 |
+
"loss": 6.459,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.02,
|
| 356 |
+
"grad_norm": 7.246520519256592,
|
| 357 |
+
"learning_rate": 2.4900000000000002e-05,
|
| 358 |
+
"loss": 6.4359,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.02,
|
| 363 |
+
"eval_loss": 6.133457660675049,
|
| 364 |
+
"eval_runtime": 422.8798,
|
| 365 |
+
"eval_samples_per_second": 50.182,
|
| 366 |
+
"eval_steps_per_second": 0.393,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.02,
|
| 371 |
+
"grad_norm": 7.1657819747924805,
|
| 372 |
+
"learning_rate": 2.54e-05,
|
| 373 |
+
"loss": 6.4372,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.02,
|
| 378 |
+
"grad_norm": 7.203813552856445,
|
| 379 |
+
"learning_rate": 2.5900000000000003e-05,
|
| 380 |
+
"loss": 6.3684,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.02,
|
| 385 |
+
"grad_norm": 6.829228401184082,
|
| 386 |
+
"learning_rate": 2.64e-05,
|
| 387 |
+
"loss": 6.3275,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.02,
|
| 392 |
+
"grad_norm": 6.641738414764404,
|
| 393 |
+
"learning_rate": 2.6900000000000003e-05,
|
| 394 |
+
"loss": 6.2923,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.02,
|
| 399 |
+
"grad_norm": 7.824960708618164,
|
| 400 |
+
"learning_rate": 2.7400000000000002e-05,
|
| 401 |
+
"loss": 6.3685,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.02,
|
| 406 |
+
"grad_norm": 6.7754364013671875,
|
| 407 |
+
"learning_rate": 2.7900000000000004e-05,
|
| 408 |
+
"loss": 6.3069,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.02,
|
| 413 |
+
"grad_norm": 7.3608903884887695,
|
| 414 |
+
"learning_rate": 2.84e-05,
|
| 415 |
+
"loss": 6.2915,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.02,
|
| 420 |
+
"grad_norm": 6.551064968109131,
|
| 421 |
+
"learning_rate": 2.8899999999999998e-05,
|
| 422 |
+
"loss": 6.1676,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.02,
|
| 427 |
+
"grad_norm": 6.588657379150391,
|
| 428 |
+
"learning_rate": 2.94e-05,
|
| 429 |
+
"loss": 6.2311,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.02,
|
| 434 |
+
"grad_norm": 6.631275177001953,
|
| 435 |
+
"learning_rate": 2.9900000000000002e-05,
|
| 436 |
+
"loss": 6.1824,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.02,
|
| 441 |
+
"grad_norm": 6.2990288734436035,
|
| 442 |
+
"learning_rate": 3.04e-05,
|
| 443 |
+
"loss": 6.1641,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.02,
|
| 448 |
+
"grad_norm": 6.6439714431762695,
|
| 449 |
+
"learning_rate": 3.09e-05,
|
| 450 |
+
"loss": 6.0125,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.03,
|
| 455 |
+
"grad_norm": 6.402431964874268,
|
| 456 |
+
"learning_rate": 3.1400000000000004e-05,
|
| 457 |
+
"loss": 6.1314,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.03,
|
| 462 |
+
"grad_norm": 5.883937358856201,
|
| 463 |
+
"learning_rate": 3.19e-05,
|
| 464 |
+
"loss": 5.9858,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.03,
|
| 469 |
+
"grad_norm": 5.988973140716553,
|
| 470 |
+
"learning_rate": 3.24e-05,
|
| 471 |
+
"loss": 5.9886,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.03,
|
| 476 |
+
"grad_norm": 6.186301231384277,
|
| 477 |
+
"learning_rate": 3.29e-05,
|
| 478 |
+
"loss": 5.9732,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.03,
|
| 483 |
+
"grad_norm": 6.2982354164123535,
|
| 484 |
+
"learning_rate": 3.3400000000000005e-05,
|
| 485 |
+
"loss": 6.0391,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.03,
|
| 490 |
+
"grad_norm": 6.037730693817139,
|
| 491 |
+
"learning_rate": 3.3900000000000004e-05,
|
| 492 |
+
"loss": 6.0547,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.03,
|
| 497 |
+
"grad_norm": 6.280949592590332,
|
| 498 |
+
"learning_rate": 3.4399999999999996e-05,
|
| 499 |
+
"loss": 5.8734,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.03,
|
| 504 |
+
"grad_norm": 6.861902236938477,
|
| 505 |
+
"learning_rate": 3.49e-05,
|
| 506 |
+
"loss": 5.8997,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.03,
|
| 511 |
+
"grad_norm": 6.4033589363098145,
|
| 512 |
+
"learning_rate": 3.54e-05,
|
| 513 |
+
"loss": 5.8111,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.03,
|
| 518 |
+
"grad_norm": 6.376819133758545,
|
| 519 |
+
"learning_rate": 3.59e-05,
|
| 520 |
+
"loss": 5.9027,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.03,
|
| 525 |
+
"grad_norm": 5.777069568634033,
|
| 526 |
+
"learning_rate": 3.6400000000000004e-05,
|
| 527 |
+
"loss": 5.727,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.03,
|
| 532 |
+
"grad_norm": 6.183162689208984,
|
| 533 |
+
"learning_rate": 3.69e-05,
|
| 534 |
+
"loss": 5.733,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.03,
|
| 539 |
+
"grad_norm": 6.658604621887207,
|
| 540 |
+
"learning_rate": 3.74e-05,
|
| 541 |
+
"loss": 5.7018,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.03,
|
| 546 |
+
"grad_norm": 6.263491153717041,
|
| 547 |
+
"learning_rate": 3.79e-05,
|
| 548 |
+
"loss": 5.7315,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.03,
|
| 553 |
+
"grad_norm": 5.86756706237793,
|
| 554 |
+
"learning_rate": 3.8400000000000005e-05,
|
| 555 |
+
"loss": 5.6637,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.03,
|
| 560 |
+
"grad_norm": 6.122657299041748,
|
| 561 |
+
"learning_rate": 3.8900000000000004e-05,
|
| 562 |
+
"loss": 5.6849,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.03,
|
| 567 |
+
"grad_norm": 5.6024580001831055,
|
| 568 |
+
"learning_rate": 3.94e-05,
|
| 569 |
+
"loss": 5.5835,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.03,
|
| 574 |
+
"grad_norm": 5.619604587554932,
|
| 575 |
+
"learning_rate": 3.99e-05,
|
| 576 |
+
"loss": 5.7,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.03,
|
| 581 |
+
"grad_norm": 5.7342352867126465,
|
| 582 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 583 |
+
"loss": 5.4825,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.03,
|
| 588 |
+
"grad_norm": 6.796237468719482,
|
| 589 |
+
"learning_rate": 4.09e-05,
|
| 590 |
+
"loss": 5.6496,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.03,
|
| 595 |
+
"grad_norm": 5.601135730743408,
|
| 596 |
+
"learning_rate": 4.14e-05,
|
| 597 |
+
"loss": 5.3526,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.03,
|
| 602 |
+
"grad_norm": 5.576679229736328,
|
| 603 |
+
"learning_rate": 4.19e-05,
|
| 604 |
+
"loss": 5.3757,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.03,
|
| 609 |
+
"grad_norm": 5.774380683898926,
|
| 610 |
+
"learning_rate": 4.24e-05,
|
| 611 |
+
"loss": 5.5164,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.03,
|
| 616 |
+
"grad_norm": 6.140038967132568,
|
| 617 |
+
"learning_rate": 4.29e-05,
|
| 618 |
+
"loss": 5.3124,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.03,
|
| 623 |
+
"grad_norm": 5.971868515014648,
|
| 624 |
+
"learning_rate": 4.3400000000000005e-05,
|
| 625 |
+
"loss": 5.3387,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.03,
|
| 630 |
+
"grad_norm": 6.431824207305908,
|
| 631 |
+
"learning_rate": 4.39e-05,
|
| 632 |
+
"loss": 5.4363,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.04,
|
| 637 |
+
"grad_norm": 6.174604892730713,
|
| 638 |
+
"learning_rate": 4.44e-05,
|
| 639 |
+
"loss": 5.282,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.04,
|
| 644 |
+
"grad_norm": 6.313474178314209,
|
| 645 |
+
"learning_rate": 4.49e-05,
|
| 646 |
+
"loss": 5.3754,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.04,
|
| 651 |
+
"grad_norm": 6.066281318664551,
|
| 652 |
+
"learning_rate": 4.5400000000000006e-05,
|
| 653 |
+
"loss": 5.3197,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.04,
|
| 658 |
+
"grad_norm": 7.4433817863464355,
|
| 659 |
+
"learning_rate": 4.5900000000000004e-05,
|
| 660 |
+
"loss": 5.3277,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.04,
|
| 665 |
+
"grad_norm": 5.884599208831787,
|
| 666 |
+
"learning_rate": 4.64e-05,
|
| 667 |
+
"loss": 5.0681,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.04,
|
| 672 |
+
"grad_norm": 6.17655611038208,
|
| 673 |
+
"learning_rate": 4.69e-05,
|
| 674 |
+
"loss": 5.1159,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.04,
|
| 679 |
+
"grad_norm": 7.090456485748291,
|
| 680 |
+
"learning_rate": 4.74e-05,
|
| 681 |
+
"loss": 5.2264,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.04,
|
| 686 |
+
"grad_norm": 6.508240699768066,
|
| 687 |
+
"learning_rate": 4.79e-05,
|
| 688 |
+
"loss": 5.2113,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.04,
|
| 693 |
+
"grad_norm": 6.5788445472717285,
|
| 694 |
+
"learning_rate": 4.8400000000000004e-05,
|
| 695 |
+
"loss": 4.9996,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.04,
|
| 700 |
+
"grad_norm": 5.722221374511719,
|
| 701 |
+
"learning_rate": 4.89e-05,
|
| 702 |
+
"loss": 4.9688,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.04,
|
| 707 |
+
"grad_norm": 5.813933849334717,
|
| 708 |
+
"learning_rate": 4.94e-05,
|
| 709 |
+
"loss": 4.8691,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.04,
|
| 714 |
+
"grad_norm": 6.425748348236084,
|
| 715 |
+
"learning_rate": 4.99e-05,
|
| 716 |
+
"loss": 4.9883,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.04,
|
| 721 |
+
"eval_loss": 4.425854682922363,
|
| 722 |
+
"eval_runtime": 422.6592,
|
| 723 |
+
"eval_samples_per_second": 50.208,
|
| 724 |
+
"eval_steps_per_second": 0.393,
|
| 725 |
+
"step": 1000
|
| 726 |
+
}
|
| 727 |
+
],
|
| 728 |
+
"logging_steps": 10,
|
| 729 |
+
"max_steps": 50400,
|
| 730 |
+
"num_input_tokens_seen": 0,
|
| 731 |
+
"num_train_epochs": 2,
|
| 732 |
+
"save_steps": 500,
|
| 733 |
+
"total_flos": 0.0,
|
| 734 |
+
"train_batch_size": 8,
|
| 735 |
+
"trial_name": null,
|
| 736 |
+
"trial_params": null
|
| 737 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37d08e731b46f2fc9ac1d4ac376bb688c70f2bf08a26eb4b0de280ef48858eb0
|
| 3 |
+
size 4539
|