Training in progress, step 1500, checkpoint
Browse files- checkpoint-1500/config.json +195 -0
- checkpoint-1500/generation_config.json +4 -0
- checkpoint-1500/model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state_0.pth +3 -0
- checkpoint-1500/rng_state_1.pth +3 -0
- checkpoint-1500/rng_state_2.pth +3 -0
- checkpoint-1500/rng_state_3.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +1095 -0
- checkpoint-1500/training_args.bin +3 -0
checkpoint-1500/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-1500/generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.39.3"
|
| 4 |
+
}
|
checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5bf96c61b9b250b2485841c08814aab3e24f0538b73e16538c82f768b393cae
|
| 3 |
+
size 579945600
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6d6cc4b60dce4813061c7419d5fc9b82dc15caef85dbd8a0a08ee01c1d40f5f
|
| 3 |
+
size 216170911
|
checkpoint-1500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a4770578b27f3090df23d9502b5eef7fb8b3058fd1b1c5027bdbf5e8c9e87a5
|
| 3 |
+
size 14960
|
checkpoint-1500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1be9eb1517e09325c3da6c6838f5be87017988a56e3fcb85a5b2bff9d118d2f4
|
| 3 |
+
size 14960
|
checkpoint-1500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af76c86464889d4825fbace0741f28aa8de234b5ccf152bddc2ec463edf32048
|
| 3 |
+
size 14960
|
checkpoint-1500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa7cbbb38b5f6bc7bc06750a6adf06f29eacc07aeadd2e052b44f47a836cc697
|
| 3 |
+
size 14960
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a675a991cc20fa35aa06537b734722c06cb62748efe1b82f701836263026548
|
| 3 |
+
size 1064
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,1095 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7249879168680522,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 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 |
+
"epoch": 0.25,
|
| 371 |
+
"grad_norm": 0.2931281328201294,
|
| 372 |
+
"learning_rate": 2.5350000000000003e-05,
|
| 373 |
+
"loss": 0.7763,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.25,
|
| 378 |
+
"grad_norm": 0.21228083968162537,
|
| 379 |
+
"learning_rate": 2.585e-05,
|
| 380 |
+
"loss": 0.7748,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.26,
|
| 385 |
+
"grad_norm": 0.26342302560806274,
|
| 386 |
+
"learning_rate": 2.6350000000000004e-05,
|
| 387 |
+
"loss": 0.789,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.26,
|
| 392 |
+
"grad_norm": 0.2840302288532257,
|
| 393 |
+
"learning_rate": 2.6850000000000002e-05,
|
| 394 |
+
"loss": 0.768,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.27,
|
| 399 |
+
"grad_norm": 0.273771196603775,
|
| 400 |
+
"learning_rate": 2.7350000000000004e-05,
|
| 401 |
+
"loss": 0.7707,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.27,
|
| 406 |
+
"grad_norm": 1.6022837162017822,
|
| 407 |
+
"learning_rate": 2.7850000000000003e-05,
|
| 408 |
+
"loss": 0.7705,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.28,
|
| 413 |
+
"grad_norm": 0.3082919716835022,
|
| 414 |
+
"learning_rate": 2.8349999999999998e-05,
|
| 415 |
+
"loss": 0.7849,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.28,
|
| 420 |
+
"grad_norm": 0.25341132283210754,
|
| 421 |
+
"learning_rate": 2.885e-05,
|
| 422 |
+
"loss": 0.7658,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.29,
|
| 427 |
+
"grad_norm": 0.2250708043575287,
|
| 428 |
+
"learning_rate": 2.935e-05,
|
| 429 |
+
"loss": 0.756,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.29,
|
| 434 |
+
"grad_norm": 0.23522531986236572,
|
| 435 |
+
"learning_rate": 2.985e-05,
|
| 436 |
+
"loss": 0.7692,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.29,
|
| 441 |
+
"grad_norm": 0.2448827624320984,
|
| 442 |
+
"learning_rate": 3.035e-05,
|
| 443 |
+
"loss": 0.7635,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3,
|
| 448 |
+
"grad_norm": 0.19717586040496826,
|
| 449 |
+
"learning_rate": 3.0850000000000004e-05,
|
| 450 |
+
"loss": 0.7548,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3,
|
| 455 |
+
"grad_norm": 0.24299098551273346,
|
| 456 |
+
"learning_rate": 3.135e-05,
|
| 457 |
+
"loss": 0.7673,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.31,
|
| 462 |
+
"grad_norm": 0.2555953562259674,
|
| 463 |
+
"learning_rate": 3.185e-05,
|
| 464 |
+
"loss": 0.7528,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.31,
|
| 469 |
+
"grad_norm": 0.2102127969264984,
|
| 470 |
+
"learning_rate": 3.235e-05,
|
| 471 |
+
"loss": 0.7678,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.32,
|
| 476 |
+
"grad_norm": 0.21767646074295044,
|
| 477 |
+
"learning_rate": 3.2850000000000006e-05,
|
| 478 |
+
"loss": 0.7564,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.32,
|
| 483 |
+
"grad_norm": 0.3582068085670471,
|
| 484 |
+
"learning_rate": 3.3350000000000004e-05,
|
| 485 |
+
"loss": 0.7645,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.33,
|
| 490 |
+
"grad_norm": 0.27804431319236755,
|
| 491 |
+
"learning_rate": 3.385e-05,
|
| 492 |
+
"loss": 0.7645,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.33,
|
| 497 |
+
"grad_norm": 0.2464047521352768,
|
| 498 |
+
"learning_rate": 3.435e-05,
|
| 499 |
+
"loss": 0.7325,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.34,
|
| 504 |
+
"grad_norm": 0.22323842346668243,
|
| 505 |
+
"learning_rate": 3.485e-05,
|
| 506 |
+
"loss": 0.7579,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.34,
|
| 511 |
+
"grad_norm": 0.28329703211784363,
|
| 512 |
+
"learning_rate": 3.535e-05,
|
| 513 |
+
"loss": 0.7399,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.35,
|
| 518 |
+
"grad_norm": 0.2471865713596344,
|
| 519 |
+
"learning_rate": 3.585e-05,
|
| 520 |
+
"loss": 0.765,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.35,
|
| 525 |
+
"grad_norm": 0.314908504486084,
|
| 526 |
+
"learning_rate": 3.635e-05,
|
| 527 |
+
"loss": 0.7529,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.36,
|
| 532 |
+
"grad_norm": 0.21466995775699615,
|
| 533 |
+
"learning_rate": 3.685e-05,
|
| 534 |
+
"loss": 0.7365,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.36,
|
| 539 |
+
"grad_norm": 0.2545580565929413,
|
| 540 |
+
"learning_rate": 3.735e-05,
|
| 541 |
+
"loss": 0.7458,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.37,
|
| 546 |
+
"grad_norm": 0.2651059329509735,
|
| 547 |
+
"learning_rate": 3.7850000000000005e-05,
|
| 548 |
+
"loss": 0.7578,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.37,
|
| 553 |
+
"grad_norm": 0.2408379763364792,
|
| 554 |
+
"learning_rate": 3.8350000000000004e-05,
|
| 555 |
+
"loss": 0.7283,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.38,
|
| 560 |
+
"grad_norm": 0.2575875520706177,
|
| 561 |
+
"learning_rate": 3.885e-05,
|
| 562 |
+
"loss": 0.7367,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.38,
|
| 567 |
+
"grad_norm": 0.28182050585746765,
|
| 568 |
+
"learning_rate": 3.935e-05,
|
| 569 |
+
"loss": 0.7784,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.39,
|
| 574 |
+
"grad_norm": 0.20579397678375244,
|
| 575 |
+
"learning_rate": 3.9850000000000006e-05,
|
| 576 |
+
"loss": 0.7533,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.39,
|
| 581 |
+
"grad_norm": 0.1906532198190689,
|
| 582 |
+
"learning_rate": 4.0350000000000005e-05,
|
| 583 |
+
"loss": 0.7544,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.4,
|
| 588 |
+
"grad_norm": 0.18311142921447754,
|
| 589 |
+
"learning_rate": 4.085e-05,
|
| 590 |
+
"loss": 0.75,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.4,
|
| 595 |
+
"grad_norm": 0.1910839080810547,
|
| 596 |
+
"learning_rate": 4.135e-05,
|
| 597 |
+
"loss": 0.7538,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.41,
|
| 602 |
+
"grad_norm": 0.2178005427122116,
|
| 603 |
+
"learning_rate": 4.185e-05,
|
| 604 |
+
"loss": 0.7456,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.41,
|
| 609 |
+
"grad_norm": 0.27642378211021423,
|
| 610 |
+
"learning_rate": 4.235e-05,
|
| 611 |
+
"loss": 0.744,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.42,
|
| 616 |
+
"grad_norm": 0.26685312390327454,
|
| 617 |
+
"learning_rate": 4.285e-05,
|
| 618 |
+
"loss": 0.7611,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.42,
|
| 623 |
+
"grad_norm": 0.2021845579147339,
|
| 624 |
+
"learning_rate": 4.335e-05,
|
| 625 |
+
"loss": 0.758,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.43,
|
| 630 |
+
"grad_norm": 0.20516808331012726,
|
| 631 |
+
"learning_rate": 4.385e-05,
|
| 632 |
+
"loss": 0.7404,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.43,
|
| 637 |
+
"grad_norm": 0.20619668066501617,
|
| 638 |
+
"learning_rate": 4.435e-05,
|
| 639 |
+
"loss": 0.7379,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.43,
|
| 644 |
+
"grad_norm": 0.22439967095851898,
|
| 645 |
+
"learning_rate": 4.4850000000000006e-05,
|
| 646 |
+
"loss": 0.7495,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.44,
|
| 651 |
+
"grad_norm": 0.2192295491695404,
|
| 652 |
+
"learning_rate": 4.5350000000000005e-05,
|
| 653 |
+
"loss": 0.7377,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.44,
|
| 658 |
+
"grad_norm": 0.26503369212150574,
|
| 659 |
+
"learning_rate": 4.585e-05,
|
| 660 |
+
"loss": 0.7481,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.45,
|
| 665 |
+
"grad_norm": 0.2249353975057602,
|
| 666 |
+
"learning_rate": 4.635e-05,
|
| 667 |
+
"loss": 0.742,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.45,
|
| 672 |
+
"grad_norm": 0.21413160860538483,
|
| 673 |
+
"learning_rate": 4.685000000000001e-05,
|
| 674 |
+
"loss": 0.7485,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.46,
|
| 679 |
+
"grad_norm": 0.20971478521823883,
|
| 680 |
+
"learning_rate": 4.735e-05,
|
| 681 |
+
"loss": 0.7339,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.46,
|
| 686 |
+
"grad_norm": 0.20295798778533936,
|
| 687 |
+
"learning_rate": 4.785e-05,
|
| 688 |
+
"loss": 0.722,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.47,
|
| 693 |
+
"grad_norm": 0.1957596242427826,
|
| 694 |
+
"learning_rate": 4.835e-05,
|
| 695 |
+
"loss": 0.7538,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.47,
|
| 700 |
+
"grad_norm": 0.18014560639858246,
|
| 701 |
+
"learning_rate": 4.885e-05,
|
| 702 |
+
"loss": 0.7251,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.48,
|
| 707 |
+
"grad_norm": 0.19334861636161804,
|
| 708 |
+
"learning_rate": 4.935e-05,
|
| 709 |
+
"loss": 0.7444,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.48,
|
| 714 |
+
"grad_norm": 0.1753440499305725,
|
| 715 |
+
"learning_rate": 4.9850000000000006e-05,
|
| 716 |
+
"loss": 0.7376,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.48,
|
| 721 |
+
"eval_loss": 0.73988938331604,
|
| 722 |
+
"eval_runtime": 42.9535,
|
| 723 |
+
"eval_samples_per_second": 46.562,
|
| 724 |
+
"eval_steps_per_second": 0.372,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.49,
|
| 729 |
+
"grad_norm": 0.24455028772354126,
|
| 730 |
+
"learning_rate": 4.99999307775404e-05,
|
| 731 |
+
"loss": 0.7404,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.49,
|
| 736 |
+
"grad_norm": 0.2149570733308792,
|
| 737 |
+
"learning_rate": 4.999959172968145e-05,
|
| 738 |
+
"loss": 0.7342,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.5,
|
| 743 |
+
"grad_norm": 0.1931283175945282,
|
| 744 |
+
"learning_rate": 4.999897014592085e-05,
|
| 745 |
+
"loss": 0.735,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.5,
|
| 750 |
+
"grad_norm": 0.2331906110048294,
|
| 751 |
+
"learning_rate": 4.999806603328352e-05,
|
| 752 |
+
"loss": 0.7145,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.51,
|
| 757 |
+
"grad_norm": 0.21177324652671814,
|
| 758 |
+
"learning_rate": 4.999687940198738e-05,
|
| 759 |
+
"loss": 0.7308,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.51,
|
| 764 |
+
"grad_norm": 0.2026621401309967,
|
| 765 |
+
"learning_rate": 4.9995410265443286e-05,
|
| 766 |
+
"loss": 0.7445,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.52,
|
| 771 |
+
"grad_norm": 0.19811251759529114,
|
| 772 |
+
"learning_rate": 4.999365864025487e-05,
|
| 773 |
+
"loss": 0.738,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.52,
|
| 778 |
+
"grad_norm": 0.1981566846370697,
|
| 779 |
+
"learning_rate": 4.9991624546218334e-05,
|
| 780 |
+
"loss": 0.7286,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.53,
|
| 785 |
+
"grad_norm": 0.17122291028499603,
|
| 786 |
+
"learning_rate": 4.9989308006322235e-05,
|
| 787 |
+
"loss": 0.737,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.53,
|
| 792 |
+
"grad_norm": 0.2182038575410843,
|
| 793 |
+
"learning_rate": 4.9986709046747225e-05,
|
| 794 |
+
"loss": 0.7354,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.54,
|
| 799 |
+
"grad_norm": 0.1823730617761612,
|
| 800 |
+
"learning_rate": 4.9983827696865764e-05,
|
| 801 |
+
"loss": 0.725,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.54,
|
| 806 |
+
"grad_norm": 0.2195768803358078,
|
| 807 |
+
"learning_rate": 4.998066398924177e-05,
|
| 808 |
+
"loss": 0.7173,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.55,
|
| 813 |
+
"grad_norm": 0.18349726498126984,
|
| 814 |
+
"learning_rate": 4.997721795963028e-05,
|
| 815 |
+
"loss": 0.7159,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.55,
|
| 820 |
+
"grad_norm": 0.2440386265516281,
|
| 821 |
+
"learning_rate": 4.997348964697699e-05,
|
| 822 |
+
"loss": 0.7171,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.56,
|
| 827 |
+
"grad_norm": 0.20371629297733307,
|
| 828 |
+
"learning_rate": 4.9969479093417894e-05,
|
| 829 |
+
"loss": 0.7179,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.56,
|
| 834 |
+
"grad_norm": 0.2982828617095947,
|
| 835 |
+
"learning_rate": 4.9965186344278746e-05,
|
| 836 |
+
"loss": 0.7222,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.57,
|
| 841 |
+
"grad_norm": 0.2097097784280777,
|
| 842 |
+
"learning_rate": 4.9960611448074555e-05,
|
| 843 |
+
"loss": 0.7174,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.57,
|
| 848 |
+
"grad_norm": 0.2264368236064911,
|
| 849 |
+
"learning_rate": 4.995575445650907e-05,
|
| 850 |
+
"loss": 0.7079,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.58,
|
| 855 |
+
"grad_norm": 0.24737605452537537,
|
| 856 |
+
"learning_rate": 4.995061542447418e-05,
|
| 857 |
+
"loss": 0.7272,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.58,
|
| 862 |
+
"grad_norm": 0.19530241191387177,
|
| 863 |
+
"learning_rate": 4.9945194410049254e-05,
|
| 864 |
+
"loss": 0.7216,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.58,
|
| 869 |
+
"grad_norm": 0.2791181802749634,
|
| 870 |
+
"learning_rate": 4.993949147450055e-05,
|
| 871 |
+
"loss": 0.712,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.59,
|
| 876 |
+
"grad_norm": 0.2095661610364914,
|
| 877 |
+
"learning_rate": 4.993350668228049e-05,
|
| 878 |
+
"loss": 0.7067,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.59,
|
| 883 |
+
"grad_norm": 0.17129307985305786,
|
| 884 |
+
"learning_rate": 4.9927240101026915e-05,
|
| 885 |
+
"loss": 0.7087,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.6,
|
| 890 |
+
"grad_norm": 0.2154540866613388,
|
| 891 |
+
"learning_rate": 4.992069180156235e-05,
|
| 892 |
+
"loss": 0.7411,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.6,
|
| 897 |
+
"grad_norm": 0.22642803192138672,
|
| 898 |
+
"learning_rate": 4.991386185789319e-05,
|
| 899 |
+
"loss": 0.7266,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.61,
|
| 904 |
+
"grad_norm": 0.19676081836223602,
|
| 905 |
+
"learning_rate": 4.9906750347208866e-05,
|
| 906 |
+
"loss": 0.7012,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.61,
|
| 911 |
+
"grad_norm": 0.2095811814069748,
|
| 912 |
+
"learning_rate": 4.989935734988098e-05,
|
| 913 |
+
"loss": 0.7162,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.62,
|
| 918 |
+
"grad_norm": 0.21455398201942444,
|
| 919 |
+
"learning_rate": 4.9891682949462385e-05,
|
| 920 |
+
"loss": 0.7177,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.62,
|
| 925 |
+
"grad_norm": 0.20205985009670258,
|
| 926 |
+
"learning_rate": 4.988372723268623e-05,
|
| 927 |
+
"loss": 0.718,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.63,
|
| 932 |
+
"grad_norm": 0.18780440092086792,
|
| 933 |
+
"learning_rate": 4.987549028946502e-05,
|
| 934 |
+
"loss": 0.7103,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.63,
|
| 939 |
+
"grad_norm": 0.20362792909145355,
|
| 940 |
+
"learning_rate": 4.986697221288956e-05,
|
| 941 |
+
"loss": 0.7304,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.64,
|
| 946 |
+
"grad_norm": 0.2820493280887604,
|
| 947 |
+
"learning_rate": 4.985817309922792e-05,
|
| 948 |
+
"loss": 0.7182,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.64,
|
| 953 |
+
"grad_norm": 0.20787598192691803,
|
| 954 |
+
"learning_rate": 4.984909304792435e-05,
|
| 955 |
+
"loss": 0.7142,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.65,
|
| 960 |
+
"grad_norm": 0.21624509990215302,
|
| 961 |
+
"learning_rate": 4.983973216159813e-05,
|
| 962 |
+
"loss": 0.7208,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.65,
|
| 967 |
+
"grad_norm": 0.19343602657318115,
|
| 968 |
+
"learning_rate": 4.983009054604246e-05,
|
| 969 |
+
"loss": 0.7097,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.66,
|
| 974 |
+
"grad_norm": 0.254402756690979,
|
| 975 |
+
"learning_rate": 4.9820168310223215e-05,
|
| 976 |
+
"loss": 0.7193,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.66,
|
| 981 |
+
"grad_norm": 0.1940561830997467,
|
| 982 |
+
"learning_rate": 4.980996556627774e-05,
|
| 983 |
+
"loss": 0.6988,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.67,
|
| 988 |
+
"grad_norm": 0.22593462467193604,
|
| 989 |
+
"learning_rate": 4.9799482429513576e-05,
|
| 990 |
+
"loss": 0.7054,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.67,
|
| 995 |
+
"grad_norm": 0.22020135819911957,
|
| 996 |
+
"learning_rate": 4.978871901840716e-05,
|
| 997 |
+
"loss": 0.7221,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.68,
|
| 1002 |
+
"grad_norm": 0.22807644307613373,
|
| 1003 |
+
"learning_rate": 4.977767545460248e-05,
|
| 1004 |
+
"loss": 0.7213,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.68,
|
| 1009 |
+
"grad_norm": 0.1925562173128128,
|
| 1010 |
+
"learning_rate": 4.9766351862909703e-05,
|
| 1011 |
+
"loss": 0.7127,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.69,
|
| 1016 |
+
"grad_norm": 0.20845136046409607,
|
| 1017 |
+
"learning_rate": 4.9754748371303775e-05,
|
| 1018 |
+
"loss": 0.7207,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.69,
|
| 1023 |
+
"grad_norm": 0.18583528697490692,
|
| 1024 |
+
"learning_rate": 4.974286511092294e-05,
|
| 1025 |
+
"loss": 0.7098,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.7,
|
| 1030 |
+
"grad_norm": 0.2019319236278534,
|
| 1031 |
+
"learning_rate": 4.973070221606732e-05,
|
| 1032 |
+
"loss": 0.7029,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.7,
|
| 1037 |
+
"grad_norm": 0.1966458261013031,
|
| 1038 |
+
"learning_rate": 4.971825982419731e-05,
|
| 1039 |
+
"loss": 0.7241,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.71,
|
| 1044 |
+
"grad_norm": 0.20924623310565948,
|
| 1045 |
+
"learning_rate": 4.970553807593214e-05,
|
| 1046 |
+
"loss": 0.7126,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.71,
|
| 1051 |
+
"grad_norm": 0.20655803382396698,
|
| 1052 |
+
"learning_rate": 4.969253711504814e-05,
|
| 1053 |
+
"loss": 0.6903,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.72,
|
| 1058 |
+
"grad_norm": 0.2179209142923355,
|
| 1059 |
+
"learning_rate": 4.967925708847727e-05,
|
| 1060 |
+
"loss": 0.683,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.72,
|
| 1065 |
+
"grad_norm": 0.2198410928249359,
|
| 1066 |
+
"learning_rate": 4.966569814630534e-05,
|
| 1067 |
+
"loss": 0.7087,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.72,
|
| 1072 |
+
"grad_norm": 0.17970815300941467,
|
| 1073 |
+
"learning_rate": 4.9651860441770374e-05,
|
| 1074 |
+
"loss": 0.7006,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.72,
|
| 1079 |
+
"eval_loss": 0.7137542366981506,
|
| 1080 |
+
"eval_runtime": 43.0052,
|
| 1081 |
+
"eval_samples_per_second": 46.506,
|
| 1082 |
+
"eval_steps_per_second": 0.372,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
}
|
| 1085 |
+
],
|
| 1086 |
+
"logging_steps": 10,
|
| 1087 |
+
"max_steps": 10345,
|
| 1088 |
+
"num_input_tokens_seen": 0,
|
| 1089 |
+
"num_train_epochs": 5,
|
| 1090 |
+
"save_steps": 500,
|
| 1091 |
+
"total_flos": 3.793360571613577e+18,
|
| 1092 |
+
"train_batch_size": 8,
|
| 1093 |
+
"trial_name": null,
|
| 1094 |
+
"trial_params": null
|
| 1095 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3814e1058daec6f70a62fab0452b08b4d1c663bae76d77a07b33001875b2afcd
|
| 3 |
+
size 5048
|