Training in progress, step 500, checkpoint
Browse files- checkpoint-500/config.json +195 -0
- checkpoint-500/generation_config.json +4 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state_0.pth +3 -0
- checkpoint-500/rng_state_1.pth +3 -0
- checkpoint-500/rng_state_2.pth +3 -0
- checkpoint-500/rng_state_3.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +379 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SrcProberForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"asm_encoder_config": {
|
| 6 |
+
"_name_or_path": "",
|
| 7 |
+
"add_cross_attention": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"LongelmForMaskedLMWithEdgePrediction"
|
| 10 |
+
],
|
| 11 |
+
"attention_probs_dropout_prob": 0.1,
|
| 12 |
+
"bad_words_ids": null,
|
| 13 |
+
"begin_suppress_tokens": null,
|
| 14 |
+
"block_size": 8,
|
| 15 |
+
"bos_token_id": 1,
|
| 16 |
+
"chunk_size_feed_forward": 0,
|
| 17 |
+
"classifier_dropout": null,
|
| 18 |
+
"cross_attention_hidden_size": null,
|
| 19 |
+
"decoder_start_token_id": null,
|
| 20 |
+
"diversity_penalty": 0.0,
|
| 21 |
+
"do_sample": false,
|
| 22 |
+
"early_stopping": false,
|
| 23 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 24 |
+
"eos_token_id": 2,
|
| 25 |
+
"ep_add_linear_projection": true,
|
| 26 |
+
"exponential_decay_length_penalty": null,
|
| 27 |
+
"finetuning_task": null,
|
| 28 |
+
"forced_bos_token_id": null,
|
| 29 |
+
"forced_eos_token_id": null,
|
| 30 |
+
"global_memory_size": 1,
|
| 31 |
+
"hidden_act": "gelu",
|
| 32 |
+
"hidden_dropout_prob": 0.1,
|
| 33 |
+
"hidden_size": 768,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1"
|
| 37 |
+
},
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 3072,
|
| 40 |
+
"is_decoder": false,
|
| 41 |
+
"is_encoder_decoder": false,
|
| 42 |
+
"label2id": {
|
| 43 |
+
"LABEL_0": 0,
|
| 44 |
+
"LABEL_1": 1
|
| 45 |
+
},
|
| 46 |
+
"layer_norm_eps": 1e-12,
|
| 47 |
+
"length_penalty": 1.0,
|
| 48 |
+
"max_blocks": 200,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 1805,
|
| 51 |
+
"max_relative_position_embeddings": 8,
|
| 52 |
+
"min_length": 0,
|
| 53 |
+
"model_type": "longelm",
|
| 54 |
+
"no_repeat_ngram_size": 0,
|
| 55 |
+
"node_size": 1,
|
| 56 |
+
"num_attention_heads": 12,
|
| 57 |
+
"num_beam_groups": 1,
|
| 58 |
+
"num_beams": 1,
|
| 59 |
+
"num_hidden_layers": 12,
|
| 60 |
+
"num_return_sequences": 1,
|
| 61 |
+
"output_attentions": false,
|
| 62 |
+
"output_hidden_states": false,
|
| 63 |
+
"output_scores": false,
|
| 64 |
+
"pad_token_id": 3,
|
| 65 |
+
"position_embedding_type": "mixed",
|
| 66 |
+
"prefix": null,
|
| 67 |
+
"problem_type": null,
|
| 68 |
+
"pruned_heads": {},
|
| 69 |
+
"remove_invalid_values": false,
|
| 70 |
+
"repetition_penalty": 1.0,
|
| 71 |
+
"return_dict": true,
|
| 72 |
+
"return_dict_in_generate": false,
|
| 73 |
+
"sep_token_id": null,
|
| 74 |
+
"suppress_tokens": null,
|
| 75 |
+
"task_specific_params": null,
|
| 76 |
+
"temperature": 1.0,
|
| 77 |
+
"tf_legacy_loss": false,
|
| 78 |
+
"tie_encoder_decoder": false,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_class": null,
|
| 81 |
+
"top_k": 50,
|
| 82 |
+
"top_p": 1.0,
|
| 83 |
+
"torch_dtype": "float32",
|
| 84 |
+
"torchscript": false,
|
| 85 |
+
"type_vocab_size": 2,
|
| 86 |
+
"typical_p": 1.0,
|
| 87 |
+
"use_bfloat16": false,
|
| 88 |
+
"use_cache": true,
|
| 89 |
+
"vocab_size": 50265
|
| 90 |
+
},
|
| 91 |
+
"asm_feature_select_strategy": "nodes",
|
| 92 |
+
"asm_token_index": 32016,
|
| 93 |
+
"ignore_index": -100,
|
| 94 |
+
"model_type": "rad-prober",
|
| 95 |
+
"pad_token_id": 2,
|
| 96 |
+
"projector_hidden_act": "gelu",
|
| 97 |
+
"src_lm_config": {
|
| 98 |
+
"_name_or_path": "codellama/CodeLlama-7b-hf",
|
| 99 |
+
"add_cross_attention": false,
|
| 100 |
+
"architectures": [
|
| 101 |
+
"LlamaForCausalLM"
|
| 102 |
+
],
|
| 103 |
+
"attention_bias": false,
|
| 104 |
+
"attention_dropout": 0.0,
|
| 105 |
+
"bad_words_ids": null,
|
| 106 |
+
"begin_suppress_tokens": null,
|
| 107 |
+
"bos_token_id": 1,
|
| 108 |
+
"chunk_size_feed_forward": 0,
|
| 109 |
+
"cross_attention_hidden_size": null,
|
| 110 |
+
"decoder_start_token_id": null,
|
| 111 |
+
"diversity_penalty": 0.0,
|
| 112 |
+
"do_sample": false,
|
| 113 |
+
"early_stopping": false,
|
| 114 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 115 |
+
"eos_token_id": 2,
|
| 116 |
+
"exponential_decay_length_penalty": null,
|
| 117 |
+
"finetuning_task": null,
|
| 118 |
+
"forced_bos_token_id": null,
|
| 119 |
+
"forced_eos_token_id": null,
|
| 120 |
+
"hidden_act": "silu",
|
| 121 |
+
"hidden_size": 4096,
|
| 122 |
+
"id2label": {
|
| 123 |
+
"0": "LABEL_0",
|
| 124 |
+
"1": "LABEL_1"
|
| 125 |
+
},
|
| 126 |
+
"initializer_range": 0.02,
|
| 127 |
+
"intermediate_size": 11008,
|
| 128 |
+
"is_decoder": false,
|
| 129 |
+
"is_encoder_decoder": false,
|
| 130 |
+
"label2id": {
|
| 131 |
+
"LABEL_0": 0,
|
| 132 |
+
"LABEL_1": 1
|
| 133 |
+
},
|
| 134 |
+
"length_penalty": 1.0,
|
| 135 |
+
"max_length": 20,
|
| 136 |
+
"max_position_embeddings": 16384,
|
| 137 |
+
"min_length": 0,
|
| 138 |
+
"model_type": "llama",
|
| 139 |
+
"no_repeat_ngram_size": 0,
|
| 140 |
+
"num_attention_heads": 32,
|
| 141 |
+
"num_beam_groups": 1,
|
| 142 |
+
"num_beams": 1,
|
| 143 |
+
"num_hidden_layers": 32,
|
| 144 |
+
"num_key_value_heads": 32,
|
| 145 |
+
"num_return_sequences": 1,
|
| 146 |
+
"output_attentions": false,
|
| 147 |
+
"output_hidden_states": false,
|
| 148 |
+
"output_scores": false,
|
| 149 |
+
"pad_token_id": null,
|
| 150 |
+
"prefix": null,
|
| 151 |
+
"pretraining_tp": 1,
|
| 152 |
+
"problem_type": null,
|
| 153 |
+
"pruned_heads": {},
|
| 154 |
+
"quantization_config": {
|
| 155 |
+
"_load_in_4bit": false,
|
| 156 |
+
"_load_in_8bit": true,
|
| 157 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 158 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 159 |
+
"bnb_4bit_quant_type": "fp4",
|
| 160 |
+
"bnb_4bit_use_double_quant": false,
|
| 161 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 162 |
+
"llm_int8_has_fp16_weight": false,
|
| 163 |
+
"llm_int8_skip_modules": null,
|
| 164 |
+
"llm_int8_threshold": 6.0,
|
| 165 |
+
"load_in_4bit": false,
|
| 166 |
+
"load_in_8bit": true,
|
| 167 |
+
"quant_method": "bitsandbytes"
|
| 168 |
+
},
|
| 169 |
+
"remove_invalid_values": false,
|
| 170 |
+
"repetition_penalty": 1.0,
|
| 171 |
+
"return_dict": true,
|
| 172 |
+
"return_dict_in_generate": false,
|
| 173 |
+
"rms_norm_eps": 1e-05,
|
| 174 |
+
"rope_scaling": null,
|
| 175 |
+
"rope_theta": 1000000,
|
| 176 |
+
"sep_token_id": null,
|
| 177 |
+
"suppress_tokens": null,
|
| 178 |
+
"task_specific_params": null,
|
| 179 |
+
"temperature": 1.0,
|
| 180 |
+
"tf_legacy_loss": false,
|
| 181 |
+
"tie_encoder_decoder": false,
|
| 182 |
+
"tie_word_embeddings": false,
|
| 183 |
+
"tokenizer_class": null,
|
| 184 |
+
"top_k": 50,
|
| 185 |
+
"top_p": 1.0,
|
| 186 |
+
"torch_dtype": "bfloat16",
|
| 187 |
+
"torchscript": false,
|
| 188 |
+
"typical_p": 1.0,
|
| 189 |
+
"use_bfloat16": false,
|
| 190 |
+
"use_cache": true,
|
| 191 |
+
"vocab_size": 32017
|
| 192 |
+
},
|
| 193 |
+
"torch_dtype": "float32",
|
| 194 |
+
"transformers_version": "4.39.3"
|
| 195 |
+
}
|
checkpoint-500/generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.39.3"
|
| 4 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85d9af09235aaae1e8e7a8da55154120874a73c99d828d68d2f8d865443ac754
|
| 3 |
+
size 579945600
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc7c95acfa61240eff3392b5b579a3ad4dae0a321fc4fd71541e070f5845725d
|
| 3 |
+
size 216170911
|
checkpoint-500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d29c1f258aef1ca2d919d62ed559329700755958f282c3d6142412bc7927faf5
|
| 3 |
+
size 14960
|
checkpoint-500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b3428f3c04970498c0508cc37bca00e41aefcb268759702e40445ceb3a732ea
|
| 3 |
+
size 14960
|
checkpoint-500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35ab702c29855d92c05dffdd70940108bd322713c0aebb8e5b95404da2f37a67
|
| 3 |
+
size 14960
|
checkpoint-500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2ee54af81f208c447755a0aaa6624efa604faced431edaae39b3377dd967275
|
| 3 |
+
size 14960
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97e63607ae730e1add3aa64c789bc44199794d0a2a10d3f0239f6e32fed29793
|
| 3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,379 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2416626389560174,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 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": 75.8236083984375,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 3.7148,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 52.23726272583008,
|
| 21 |
+
"learning_rate": 9e-07,
|
| 22 |
+
"loss": 3.2721,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 35.391998291015625,
|
| 28 |
+
"learning_rate": 1.4000000000000001e-06,
|
| 29 |
+
"loss": 2.4262,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"grad_norm": 15.225934028625488,
|
| 35 |
+
"learning_rate": 1.9e-06,
|
| 36 |
+
"loss": 1.8828,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 13.488654136657715,
|
| 42 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 43 |
+
"loss": 1.5398,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"grad_norm": 8.773133277893066,
|
| 49 |
+
"learning_rate": 2.8500000000000002e-06,
|
| 50 |
+
"loss": 1.2772,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"grad_norm": 6.736795902252197,
|
| 56 |
+
"learning_rate": 3.3500000000000005e-06,
|
| 57 |
+
"loss": 1.1159,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04,
|
| 62 |
+
"grad_norm": 2.9463019371032715,
|
| 63 |
+
"learning_rate": 3.85e-06,
|
| 64 |
+
"loss": 0.9883,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"grad_norm": 1.3851969242095947,
|
| 70 |
+
"learning_rate": 4.35e-06,
|
| 71 |
+
"loss": 0.902,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.05,
|
| 76 |
+
"grad_norm": 1.4642181396484375,
|
| 77 |
+
"learning_rate": 4.85e-06,
|
| 78 |
+
"loss": 0.8701,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"grad_norm": 0.6514687538146973,
|
| 84 |
+
"learning_rate": 5.3500000000000004e-06,
|
| 85 |
+
"loss": 0.8548,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.06,
|
| 90 |
+
"grad_norm": 0.4448617994785309,
|
| 91 |
+
"learning_rate": 5.850000000000001e-06,
|
| 92 |
+
"loss": 0.8038,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"grad_norm": 0.5425733327865601,
|
| 98 |
+
"learning_rate": 6.35e-06,
|
| 99 |
+
"loss": 0.825,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.07,
|
| 104 |
+
"grad_norm": 0.47352057695388794,
|
| 105 |
+
"learning_rate": 6.8500000000000005e-06,
|
| 106 |
+
"loss": 0.812,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"grad_norm": 0.40401744842529297,
|
| 112 |
+
"learning_rate": 7.35e-06,
|
| 113 |
+
"loss": 0.7912,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08,
|
| 118 |
+
"grad_norm": 0.3112718164920807,
|
| 119 |
+
"learning_rate": 7.850000000000001e-06,
|
| 120 |
+
"loss": 0.8057,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08,
|
| 125 |
+
"grad_norm": 0.45351892709732056,
|
| 126 |
+
"learning_rate": 8.350000000000001e-06,
|
| 127 |
+
"loss": 0.7912,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.09,
|
| 132 |
+
"grad_norm": 0.38080641627311707,
|
| 133 |
+
"learning_rate": 8.85e-06,
|
| 134 |
+
"loss": 0.7956,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.09,
|
| 139 |
+
"grad_norm": 0.22949431836605072,
|
| 140 |
+
"learning_rate": 9.35e-06,
|
| 141 |
+
"loss": 0.7785,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.1,
|
| 146 |
+
"grad_norm": 0.8331744074821472,
|
| 147 |
+
"learning_rate": 9.85e-06,
|
| 148 |
+
"loss": 0.7769,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1,
|
| 153 |
+
"grad_norm": 0.30213871598243713,
|
| 154 |
+
"learning_rate": 1.035e-05,
|
| 155 |
+
"loss": 0.7797,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.11,
|
| 160 |
+
"grad_norm": 0.32015591859817505,
|
| 161 |
+
"learning_rate": 1.0850000000000001e-05,
|
| 162 |
+
"loss": 0.7941,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.11,
|
| 167 |
+
"grad_norm": 0.22447015345096588,
|
| 168 |
+
"learning_rate": 1.1350000000000001e-05,
|
| 169 |
+
"loss": 0.8014,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.12,
|
| 174 |
+
"grad_norm": 0.2546006143093109,
|
| 175 |
+
"learning_rate": 1.185e-05,
|
| 176 |
+
"loss": 0.771,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12,
|
| 181 |
+
"grad_norm": 0.23833389580249786,
|
| 182 |
+
"learning_rate": 1.235e-05,
|
| 183 |
+
"loss": 0.7956,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.13,
|
| 188 |
+
"grad_norm": 0.1831669956445694,
|
| 189 |
+
"learning_rate": 1.285e-05,
|
| 190 |
+
"loss": 0.7833,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.13,
|
| 195 |
+
"grad_norm": 0.19860319793224335,
|
| 196 |
+
"learning_rate": 1.3350000000000001e-05,
|
| 197 |
+
"loss": 0.7956,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.14,
|
| 202 |
+
"grad_norm": 0.21220380067825317,
|
| 203 |
+
"learning_rate": 1.3850000000000001e-05,
|
| 204 |
+
"loss": 0.7942,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.14,
|
| 209 |
+
"grad_norm": 0.26025038957595825,
|
| 210 |
+
"learning_rate": 1.435e-05,
|
| 211 |
+
"loss": 0.7877,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.14,
|
| 216 |
+
"grad_norm": 0.2029470056295395,
|
| 217 |
+
"learning_rate": 1.485e-05,
|
| 218 |
+
"loss": 0.7637,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15,
|
| 223 |
+
"grad_norm": 0.21639183163642883,
|
| 224 |
+
"learning_rate": 1.535e-05,
|
| 225 |
+
"loss": 0.7885,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.15,
|
| 230 |
+
"grad_norm": 0.23670387268066406,
|
| 231 |
+
"learning_rate": 1.5850000000000002e-05,
|
| 232 |
+
"loss": 0.7558,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.16,
|
| 237 |
+
"grad_norm": 0.2855335772037506,
|
| 238 |
+
"learning_rate": 1.635e-05,
|
| 239 |
+
"loss": 0.7854,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.16,
|
| 244 |
+
"grad_norm": 0.21515759825706482,
|
| 245 |
+
"learning_rate": 1.6850000000000003e-05,
|
| 246 |
+
"loss": 0.7577,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.17,
|
| 251 |
+
"grad_norm": 0.18981383740901947,
|
| 252 |
+
"learning_rate": 1.7349999999999998e-05,
|
| 253 |
+
"loss": 0.7802,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.17,
|
| 258 |
+
"grad_norm": 0.2674611508846283,
|
| 259 |
+
"learning_rate": 1.785e-05,
|
| 260 |
+
"loss": 0.7809,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.18,
|
| 265 |
+
"grad_norm": 0.24821774661540985,
|
| 266 |
+
"learning_rate": 1.8350000000000002e-05,
|
| 267 |
+
"loss": 0.7965,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.18,
|
| 272 |
+
"grad_norm": 0.3644929528236389,
|
| 273 |
+
"learning_rate": 1.885e-05,
|
| 274 |
+
"loss": 0.7957,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.19,
|
| 279 |
+
"grad_norm": 0.3568972647190094,
|
| 280 |
+
"learning_rate": 1.9350000000000003e-05,
|
| 281 |
+
"loss": 0.7882,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.19,
|
| 286 |
+
"grad_norm": 0.3236319422721863,
|
| 287 |
+
"learning_rate": 1.985e-05,
|
| 288 |
+
"loss": 0.7841,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2,
|
| 293 |
+
"grad_norm": 0.24553723633289337,
|
| 294 |
+
"learning_rate": 2.035e-05,
|
| 295 |
+
"loss": 0.7824,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2,
|
| 300 |
+
"grad_norm": 0.1855400949716568,
|
| 301 |
+
"learning_rate": 2.085e-05,
|
| 302 |
+
"loss": 0.7645,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.21,
|
| 307 |
+
"grad_norm": 0.26212435960769653,
|
| 308 |
+
"learning_rate": 2.135e-05,
|
| 309 |
+
"loss": 0.7824,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.21,
|
| 314 |
+
"grad_norm": 0.3167509138584137,
|
| 315 |
+
"learning_rate": 2.1850000000000003e-05,
|
| 316 |
+
"loss": 0.7908,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.22,
|
| 321 |
+
"grad_norm": 0.21845023334026337,
|
| 322 |
+
"learning_rate": 2.235e-05,
|
| 323 |
+
"loss": 0.7888,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.22,
|
| 328 |
+
"grad_norm": 0.30318892002105713,
|
| 329 |
+
"learning_rate": 2.2850000000000003e-05,
|
| 330 |
+
"loss": 0.7682,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.23,
|
| 335 |
+
"grad_norm": 0.28828638792037964,
|
| 336 |
+
"learning_rate": 2.3350000000000002e-05,
|
| 337 |
+
"loss": 0.7588,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.23,
|
| 342 |
+
"grad_norm": 0.2422240674495697,
|
| 343 |
+
"learning_rate": 2.385e-05,
|
| 344 |
+
"loss": 0.7787,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.24,
|
| 349 |
+
"grad_norm": 0.3579326272010803,
|
| 350 |
+
"learning_rate": 2.435e-05,
|
| 351 |
+
"loss": 0.7932,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.24,
|
| 356 |
+
"grad_norm": 0.3549540042877197,
|
| 357 |
+
"learning_rate": 2.485e-05,
|
| 358 |
+
"loss": 0.7634,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.24,
|
| 363 |
+
"eval_loss": 0.7744565606117249,
|
| 364 |
+
"eval_runtime": 43.9626,
|
| 365 |
+
"eval_samples_per_second": 45.493,
|
| 366 |
+
"eval_steps_per_second": 0.364,
|
| 367 |
+
"step": 500
|
| 368 |
+
}
|
| 369 |
+
],
|
| 370 |
+
"logging_steps": 10,
|
| 371 |
+
"max_steps": 10345,
|
| 372 |
+
"num_input_tokens_seen": 0,
|
| 373 |
+
"num_train_epochs": 5,
|
| 374 |
+
"save_steps": 500,
|
| 375 |
+
"total_flos": 1.2648108400962437e+18,
|
| 376 |
+
"train_batch_size": 8,
|
| 377 |
+
"trial_name": null,
|
| 378 |
+
"trial_params": null
|
| 379 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3814e1058daec6f70a62fab0452b08b4d1c663bae76d77a07b33001875b2afcd
|
| 3 |
+
size 5048
|