Training in progress, step 1000, checkpoint
Browse files- checkpoint-1000/config.json +195 -0
- checkpoint-1000/generation_config.json +4 -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/rng_state_2.pth +3 -0
- checkpoint-1000/rng_state_3.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 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-13b-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": 5120,
|
| 122 |
+
"id2label": {
|
| 123 |
+
"0": "LABEL_0",
|
| 124 |
+
"1": "LABEL_1"
|
| 125 |
+
},
|
| 126 |
+
"initializer_range": 0.02,
|
| 127 |
+
"intermediate_size": 13824,
|
| 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": 40,
|
| 141 |
+
"num_beam_groups": 1,
|
| 142 |
+
"num_beams": 1,
|
| 143 |
+
"num_hidden_layers": 40,
|
| 144 |
+
"num_key_value_heads": 40,
|
| 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-1000/generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.39.3"
|
| 4 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:222c696830a87c65162a6a6daddcbcc73b17b972981c890b92ff4f88da895266
|
| 3 |
+
size 620848256
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92a300df87804bc1512f7d0ab51b1b24c06e2121b561e7d4e2643f95e3adb82b
|
| 3 |
+
size 297976223
|
checkpoint-1000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e42c893bb96b4ccb227fe2ff67121708f43f0f9aad3c0d73bb103df7095a1b2f
|
| 3 |
+
size 14960
|
checkpoint-1000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a8e64ac451f29a3e703cd433c25d291bfb31f0b6ca3a814c0918d87cf47c7bf
|
| 3 |
+
size 14960
|
checkpoint-1000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4beca062484c6a48c203feba5275c5667f87d43e495f8c514953380d7790137e
|
| 3 |
+
size 14960
|
checkpoint-1000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05fa698d57eb83dbbee489f139a32ec85dcfca39950157083d3e05de6a32538b
|
| 3 |
+
size 14960
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dfeba62cd7bf42ed85d9eb6c75e91b9d603b7380f345fad23f16adb49c5715b
|
| 3 |
+
size 1064
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,737 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2416626389560174,
|
| 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": NaN,
|
| 14 |
+
"learning_rate": 2.0000000000000002e-07,
|
| 15 |
+
"loss": 2.0414,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0,
|
| 20 |
+
"grad_norm": 53.515953063964844,
|
| 21 |
+
"learning_rate": 6.5e-07,
|
| 22 |
+
"loss": 1.8355,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 27.920907974243164,
|
| 28 |
+
"learning_rate": 1.15e-06,
|
| 29 |
+
"loss": 1.5172,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 20.47172737121582,
|
| 35 |
+
"learning_rate": 1.65e-06,
|
| 36 |
+
"loss": 1.2654,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"grad_norm": 8.903529167175293,
|
| 42 |
+
"learning_rate": 2.1499999999999997e-06,
|
| 43 |
+
"loss": 1.1095,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01,
|
| 48 |
+
"grad_norm": 5.902841567993164,
|
| 49 |
+
"learning_rate": 2.65e-06,
|
| 50 |
+
"loss": 1.0017,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"grad_norm": 2.9340908527374268,
|
| 56 |
+
"learning_rate": 3.1500000000000003e-06,
|
| 57 |
+
"loss": 0.8846,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.02,
|
| 62 |
+
"grad_norm": 8.701367378234863,
|
| 63 |
+
"learning_rate": 3.6499999999999998e-06,
|
| 64 |
+
"loss": 0.8572,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"grad_norm": 1.3205362558364868,
|
| 70 |
+
"learning_rate": 4.15e-06,
|
| 71 |
+
"loss": 0.839,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02,
|
| 76 |
+
"grad_norm": 3.0334558486938477,
|
| 77 |
+
"learning_rate": 4.65e-06,
|
| 78 |
+
"loss": 0.7838,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"grad_norm": 1.8086520433425903,
|
| 84 |
+
"learning_rate": 5.15e-06,
|
| 85 |
+
"loss": 0.7782,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.03,
|
| 90 |
+
"grad_norm": 29.50135040283203,
|
| 91 |
+
"learning_rate": 5.65e-06,
|
| 92 |
+
"loss": 0.7883,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"grad_norm": 3.2708683013916016,
|
| 98 |
+
"learning_rate": 6.15e-06,
|
| 99 |
+
"loss": 0.7961,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03,
|
| 104 |
+
"grad_norm": 33.43790817260742,
|
| 105 |
+
"learning_rate": 6.650000000000001e-06,
|
| 106 |
+
"loss": 0.7626,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"grad_norm": 1.2334959506988525,
|
| 112 |
+
"learning_rate": 7.15e-06,
|
| 113 |
+
"loss": 0.7732,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04,
|
| 118 |
+
"grad_norm": 1.7489686012268066,
|
| 119 |
+
"learning_rate": 7.65e-06,
|
| 120 |
+
"loss": 0.7715,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"grad_norm": 3.358823776245117,
|
| 126 |
+
"learning_rate": 8.15e-06,
|
| 127 |
+
"loss": 0.7778,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.04,
|
| 132 |
+
"grad_norm": 4.348245620727539,
|
| 133 |
+
"learning_rate": 8.65e-06,
|
| 134 |
+
"loss": 0.7619,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"grad_norm": 0.9023125767707825,
|
| 140 |
+
"learning_rate": 9.15e-06,
|
| 141 |
+
"loss": 0.7746,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.05,
|
| 146 |
+
"grad_norm": 0.9158114790916443,
|
| 147 |
+
"learning_rate": 9.65e-06,
|
| 148 |
+
"loss": 0.7592,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"grad_norm": 0.6256226301193237,
|
| 154 |
+
"learning_rate": 1.0150000000000001e-05,
|
| 155 |
+
"loss": 0.7787,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.05,
|
| 160 |
+
"grad_norm": 0.3805778920650482,
|
| 161 |
+
"learning_rate": 1.065e-05,
|
| 162 |
+
"loss": 0.7811,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"grad_norm": 0.6968041062355042,
|
| 168 |
+
"learning_rate": 1.115e-05,
|
| 169 |
+
"loss": 0.73,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.06,
|
| 174 |
+
"grad_norm": 0.9035410284996033,
|
| 175 |
+
"learning_rate": 1.1650000000000002e-05,
|
| 176 |
+
"loss": 0.7518,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"grad_norm": 1.6727488040924072,
|
| 182 |
+
"learning_rate": 1.215e-05,
|
| 183 |
+
"loss": 0.7805,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.06,
|
| 188 |
+
"grad_norm": 0.4153461158275604,
|
| 189 |
+
"learning_rate": 1.2650000000000001e-05,
|
| 190 |
+
"loss": 0.7706,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"grad_norm": 1.4846651554107666,
|
| 196 |
+
"learning_rate": 1.3150000000000001e-05,
|
| 197 |
+
"loss": 0.7492,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.07,
|
| 202 |
+
"grad_norm": 2.6631388664245605,
|
| 203 |
+
"learning_rate": 1.3650000000000001e-05,
|
| 204 |
+
"loss": 0.7681,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"grad_norm": 0.6325013041496277,
|
| 210 |
+
"learning_rate": 1.415e-05,
|
| 211 |
+
"loss": 0.7753,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.07,
|
| 216 |
+
"grad_norm": 0.877907395362854,
|
| 217 |
+
"learning_rate": 1.465e-05,
|
| 218 |
+
"loss": 0.7188,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.07,
|
| 223 |
+
"grad_norm": 0.37142279744148254,
|
| 224 |
+
"learning_rate": 1.515e-05,
|
| 225 |
+
"loss": 0.7204,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.08,
|
| 230 |
+
"grad_norm": 0.7337246537208557,
|
| 231 |
+
"learning_rate": 1.565e-05,
|
| 232 |
+
"loss": 0.778,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.08,
|
| 237 |
+
"grad_norm": 0.5847220420837402,
|
| 238 |
+
"learning_rate": 1.6150000000000003e-05,
|
| 239 |
+
"loss": 0.7288,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.08,
|
| 244 |
+
"grad_norm": 3.745180606842041,
|
| 245 |
+
"learning_rate": 1.665e-05,
|
| 246 |
+
"loss": 0.7531,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.08,
|
| 251 |
+
"grad_norm": 0.357301265001297,
|
| 252 |
+
"learning_rate": 1.7150000000000004e-05,
|
| 253 |
+
"loss": 0.7448,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.09,
|
| 258 |
+
"grad_norm": 0.9032486081123352,
|
| 259 |
+
"learning_rate": 1.765e-05,
|
| 260 |
+
"loss": 0.7651,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.09,
|
| 265 |
+
"grad_norm": 0.2864232361316681,
|
| 266 |
+
"learning_rate": 1.815e-05,
|
| 267 |
+
"loss": 0.7193,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.09,
|
| 272 |
+
"grad_norm": 1.8560261726379395,
|
| 273 |
+
"learning_rate": 1.865e-05,
|
| 274 |
+
"loss": 0.7421,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.09,
|
| 279 |
+
"grad_norm": 0.2971792221069336,
|
| 280 |
+
"learning_rate": 1.915e-05,
|
| 281 |
+
"loss": 0.7171,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1,
|
| 286 |
+
"grad_norm": 0.40850627422332764,
|
| 287 |
+
"learning_rate": 1.9650000000000003e-05,
|
| 288 |
+
"loss": 0.7459,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.1,
|
| 293 |
+
"grad_norm": 0.3934139311313629,
|
| 294 |
+
"learning_rate": 2.0150000000000002e-05,
|
| 295 |
+
"loss": 0.7205,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.1,
|
| 300 |
+
"grad_norm": 1.8674131631851196,
|
| 301 |
+
"learning_rate": 2.065e-05,
|
| 302 |
+
"loss": 0.752,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.1,
|
| 307 |
+
"grad_norm": 0.36707818508148193,
|
| 308 |
+
"learning_rate": 2.115e-05,
|
| 309 |
+
"loss": 0.7494,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.11,
|
| 314 |
+
"grad_norm": 0.5044310092926025,
|
| 315 |
+
"learning_rate": 2.165e-05,
|
| 316 |
+
"loss": 0.7595,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.11,
|
| 321 |
+
"grad_norm": 1.9025150537490845,
|
| 322 |
+
"learning_rate": 2.215e-05,
|
| 323 |
+
"loss": 0.7379,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.11,
|
| 328 |
+
"grad_norm": 0.5004140138626099,
|
| 329 |
+
"learning_rate": 2.265e-05,
|
| 330 |
+
"loss": 0.7886,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.11,
|
| 335 |
+
"grad_norm": 3.544482707977295,
|
| 336 |
+
"learning_rate": 2.3150000000000004e-05,
|
| 337 |
+
"loss": 0.7259,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.12,
|
| 342 |
+
"grad_norm": 0.33023321628570557,
|
| 343 |
+
"learning_rate": 2.365e-05,
|
| 344 |
+
"loss": 0.7333,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.12,
|
| 349 |
+
"grad_norm": 0.3548080325126648,
|
| 350 |
+
"learning_rate": 2.415e-05,
|
| 351 |
+
"loss": 0.7527,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.12,
|
| 356 |
+
"grad_norm": 0.42450150847435,
|
| 357 |
+
"learning_rate": 2.465e-05,
|
| 358 |
+
"loss": 0.7443,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.12,
|
| 363 |
+
"eval_loss": 0.7428915500640869,
|
| 364 |
+
"eval_runtime": 68.3143,
|
| 365 |
+
"eval_samples_per_second": 29.276,
|
| 366 |
+
"eval_steps_per_second": 0.922,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.12,
|
| 371 |
+
"grad_norm": 0.3299656808376312,
|
| 372 |
+
"learning_rate": 2.515e-05,
|
| 373 |
+
"loss": 0.7447,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.13,
|
| 378 |
+
"grad_norm": 0.27258285880088806,
|
| 379 |
+
"learning_rate": 2.5650000000000003e-05,
|
| 380 |
+
"loss": 0.7278,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.13,
|
| 385 |
+
"grad_norm": 0.23753009736537933,
|
| 386 |
+
"learning_rate": 2.6150000000000002e-05,
|
| 387 |
+
"loss": 0.7721,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.13,
|
| 392 |
+
"grad_norm": 1.1074901819229126,
|
| 393 |
+
"learning_rate": 2.6650000000000004e-05,
|
| 394 |
+
"loss": 0.7383,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.13,
|
| 399 |
+
"grad_norm": 0.428067147731781,
|
| 400 |
+
"learning_rate": 2.7150000000000003e-05,
|
| 401 |
+
"loss": 0.7508,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.14,
|
| 406 |
+
"grad_norm": 0.35956478118896484,
|
| 407 |
+
"learning_rate": 2.7650000000000005e-05,
|
| 408 |
+
"loss": 0.7461,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.14,
|
| 413 |
+
"grad_norm": 0.23017314076423645,
|
| 414 |
+
"learning_rate": 2.815e-05,
|
| 415 |
+
"loss": 0.7463,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.14,
|
| 420 |
+
"grad_norm": 0.20370900630950928,
|
| 421 |
+
"learning_rate": 2.865e-05,
|
| 422 |
+
"loss": 0.7405,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.14,
|
| 427 |
+
"grad_norm": 0.24586541950702667,
|
| 428 |
+
"learning_rate": 2.915e-05,
|
| 429 |
+
"loss": 0.6964,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.14,
|
| 434 |
+
"grad_norm": 0.27857884764671326,
|
| 435 |
+
"learning_rate": 2.965e-05,
|
| 436 |
+
"loss": 0.7376,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.15,
|
| 441 |
+
"grad_norm": 0.2655833065509796,
|
| 442 |
+
"learning_rate": 3.015e-05,
|
| 443 |
+
"loss": 0.7496,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.15,
|
| 448 |
+
"grad_norm": 0.17174670100212097,
|
| 449 |
+
"learning_rate": 3.065e-05,
|
| 450 |
+
"loss": 0.7219,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.15,
|
| 455 |
+
"grad_norm": 0.22892743349075317,
|
| 456 |
+
"learning_rate": 3.115e-05,
|
| 457 |
+
"loss": 0.7111,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.15,
|
| 462 |
+
"grad_norm": 0.5913789868354797,
|
| 463 |
+
"learning_rate": 3.1650000000000004e-05,
|
| 464 |
+
"loss": 0.7097,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.16,
|
| 469 |
+
"grad_norm": 0.25620004534721375,
|
| 470 |
+
"learning_rate": 3.215e-05,
|
| 471 |
+
"loss": 0.7306,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.16,
|
| 476 |
+
"grad_norm": 0.3311476409435272,
|
| 477 |
+
"learning_rate": 3.265e-05,
|
| 478 |
+
"loss": 0.7406,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.16,
|
| 483 |
+
"grad_norm": 0.4708893597126007,
|
| 484 |
+
"learning_rate": 3.3150000000000006e-05,
|
| 485 |
+
"loss": 0.7071,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.16,
|
| 490 |
+
"grad_norm": 0.22469288110733032,
|
| 491 |
+
"learning_rate": 3.3650000000000005e-05,
|
| 492 |
+
"loss": 0.7116,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.17,
|
| 497 |
+
"grad_norm": 0.2909330725669861,
|
| 498 |
+
"learning_rate": 3.415e-05,
|
| 499 |
+
"loss": 0.7592,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.17,
|
| 504 |
+
"grad_norm": 0.21274766325950623,
|
| 505 |
+
"learning_rate": 3.465e-05,
|
| 506 |
+
"loss": 0.7144,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.17,
|
| 511 |
+
"grad_norm": 0.23929230868816376,
|
| 512 |
+
"learning_rate": 3.515e-05,
|
| 513 |
+
"loss": 0.7382,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.17,
|
| 518 |
+
"grad_norm": 0.3021218180656433,
|
| 519 |
+
"learning_rate": 3.565e-05,
|
| 520 |
+
"loss": 0.7287,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.18,
|
| 525 |
+
"grad_norm": 0.23557321727275848,
|
| 526 |
+
"learning_rate": 3.615e-05,
|
| 527 |
+
"loss": 0.7475,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.18,
|
| 532 |
+
"grad_norm": 0.22648084163665771,
|
| 533 |
+
"learning_rate": 3.665e-05,
|
| 534 |
+
"loss": 0.7457,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.18,
|
| 539 |
+
"grad_norm": 0.2707761824131012,
|
| 540 |
+
"learning_rate": 3.715e-05,
|
| 541 |
+
"loss": 0.7322,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.18,
|
| 546 |
+
"grad_norm": 0.2799661457538605,
|
| 547 |
+
"learning_rate": 3.765e-05,
|
| 548 |
+
"loss": 0.7682,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.19,
|
| 553 |
+
"grad_norm": 0.326861172914505,
|
| 554 |
+
"learning_rate": 3.8150000000000006e-05,
|
| 555 |
+
"loss": 0.73,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.19,
|
| 560 |
+
"grad_norm": 0.31985723972320557,
|
| 561 |
+
"learning_rate": 3.8650000000000004e-05,
|
| 562 |
+
"loss": 0.744,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.19,
|
| 567 |
+
"grad_norm": 0.21637533605098724,
|
| 568 |
+
"learning_rate": 3.915e-05,
|
| 569 |
+
"loss": 0.7161,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.19,
|
| 574 |
+
"grad_norm": 0.26102888584136963,
|
| 575 |
+
"learning_rate": 3.965e-05,
|
| 576 |
+
"loss": 0.7553,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.2,
|
| 581 |
+
"grad_norm": 0.2469174712896347,
|
| 582 |
+
"learning_rate": 4.015000000000001e-05,
|
| 583 |
+
"loss": 0.7444,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.2,
|
| 588 |
+
"grad_norm": 0.2022310495376587,
|
| 589 |
+
"learning_rate": 4.065e-05,
|
| 590 |
+
"loss": 0.7089,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.2,
|
| 595 |
+
"grad_norm": 0.1729898750782013,
|
| 596 |
+
"learning_rate": 4.115e-05,
|
| 597 |
+
"loss": 0.7122,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.2,
|
| 602 |
+
"grad_norm": 0.22450707852840424,
|
| 603 |
+
"learning_rate": 4.165e-05,
|
| 604 |
+
"loss": 0.7099,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.21,
|
| 609 |
+
"grad_norm": 0.22389698028564453,
|
| 610 |
+
"learning_rate": 4.215e-05,
|
| 611 |
+
"loss": 0.7445,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.21,
|
| 616 |
+
"grad_norm": 0.24962696433067322,
|
| 617 |
+
"learning_rate": 4.265e-05,
|
| 618 |
+
"loss": 0.7052,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.21,
|
| 623 |
+
"grad_norm": 0.23780404031276703,
|
| 624 |
+
"learning_rate": 4.315e-05,
|
| 625 |
+
"loss": 0.7423,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.21,
|
| 630 |
+
"grad_norm": 0.2434270679950714,
|
| 631 |
+
"learning_rate": 4.3650000000000004e-05,
|
| 632 |
+
"loss": 0.7291,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.22,
|
| 637 |
+
"grad_norm": 0.3332350552082062,
|
| 638 |
+
"learning_rate": 4.415e-05,
|
| 639 |
+
"loss": 0.7306,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.22,
|
| 644 |
+
"grad_norm": 0.5084495544433594,
|
| 645 |
+
"learning_rate": 4.465e-05,
|
| 646 |
+
"loss": 0.735,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.22,
|
| 651 |
+
"grad_norm": 0.27552103996276855,
|
| 652 |
+
"learning_rate": 4.5150000000000006e-05,
|
| 653 |
+
"loss": 0.7082,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.22,
|
| 658 |
+
"grad_norm": 0.2184416800737381,
|
| 659 |
+
"learning_rate": 4.5650000000000005e-05,
|
| 660 |
+
"loss": 0.7066,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.22,
|
| 665 |
+
"grad_norm": 0.21738290786743164,
|
| 666 |
+
"learning_rate": 4.6150000000000004e-05,
|
| 667 |
+
"loss": 0.6977,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.23,
|
| 672 |
+
"grad_norm": 0.21888123452663422,
|
| 673 |
+
"learning_rate": 4.665e-05,
|
| 674 |
+
"loss": 0.7083,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.23,
|
| 679 |
+
"grad_norm": 0.2516074776649475,
|
| 680 |
+
"learning_rate": 4.715e-05,
|
| 681 |
+
"loss": 0.7451,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.23,
|
| 686 |
+
"grad_norm": 0.39361557364463806,
|
| 687 |
+
"learning_rate": 4.765e-05,
|
| 688 |
+
"loss": 0.7013,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.23,
|
| 693 |
+
"grad_norm": 0.2461744099855423,
|
| 694 |
+
"learning_rate": 4.815e-05,
|
| 695 |
+
"loss": 0.7325,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.24,
|
| 700 |
+
"grad_norm": 0.2554089426994324,
|
| 701 |
+
"learning_rate": 4.8650000000000003e-05,
|
| 702 |
+
"loss": 0.7384,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.24,
|
| 707 |
+
"grad_norm": 0.2717374861240387,
|
| 708 |
+
"learning_rate": 4.915e-05,
|
| 709 |
+
"loss": 0.7172,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.24,
|
| 714 |
+
"grad_norm": 0.35919347405433655,
|
| 715 |
+
"learning_rate": 4.965e-05,
|
| 716 |
+
"loss": 0.6851,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.24,
|
| 721 |
+
"eval_loss": 0.7169972658157349,
|
| 722 |
+
"eval_runtime": 67.4497,
|
| 723 |
+
"eval_samples_per_second": 29.652,
|
| 724 |
+
"eval_steps_per_second": 0.934,
|
| 725 |
+
"step": 1000
|
| 726 |
+
}
|
| 727 |
+
],
|
| 728 |
+
"logging_steps": 10,
|
| 729 |
+
"max_steps": 20690,
|
| 730 |
+
"num_input_tokens_seen": 0,
|
| 731 |
+
"num_train_epochs": 5,
|
| 732 |
+
"save_steps": 500,
|
| 733 |
+
"total_flos": 2.1633806834671288e+18,
|
| 734 |
+
"train_batch_size": 4,
|
| 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:fd6a31d2da7b4686068d511137b843e541147626d5878a410233f3ef91ae5dc6
|
| 3 |
+
size 5048
|