prathmeshadsod commited on
Commit
188a5d8
·
verified ·
1 Parent(s): cb3bcef

Upload 8 files

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  assets/bondshift-training.png filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  assets/bondshift-training.png filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": [],
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 32,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "v_proj",
29
+ "o_proj",
30
+ "up_proj",
31
+ "k_proj",
32
+ "down_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f9f7ddc73f92e5a65e5da1787913fbaaf48ad5b31903ce9f583b3ea3cf30ab9
3
+ size 1656902648
chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 8192,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 28672,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 64,
19
+ "num_hidden_layers": 80,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128009,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_parameters": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_theta": 500000.0,
30
+ "rope_type": "llama3"
31
+ },
32
+ "tie_word_embeddings": false,
33
+ "transformers_version": "5.10.1",
34
+ "use_cache": false,
35
+ "vocab_size": 128256,
36
+ "torch_dtype": "bfloat16"
37
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|begin_of_text|>",
3
+ "eos_token": "<|eot_id|>",
4
+ "pad_token": "<|eot_id|>"
5
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin_of_text|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|eot_id|>",
6
+ "is_local": false,
7
+ "local_files_only": true,
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 131072,
13
+ "pad_token": "<|eot_id|>",
14
+ "padding_side": "right",
15
+ "tokenizer_class": "TokenizersBackend"
16
+ }
trainer_state.json ADDED
@@ -0,0 +1,1544 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 42,
7
+ "global_step": 210,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.014285714285714285,
14
+ "grad_norm": 0.2320670485496521,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.4560546875,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.02857142857142857,
21
+ "grad_norm": 0.19893766939640045,
22
+ "learning_rate": 1.4285714285714285e-05,
23
+ "loss": 1.416015625,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.04285714285714286,
28
+ "grad_norm": 0.21485203504562378,
29
+ "learning_rate": 2.857142857142857e-05,
30
+ "loss": 1.427734375,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.05714285714285714,
35
+ "grad_norm": 0.17585554718971252,
36
+ "learning_rate": 4.2857142857142856e-05,
37
+ "loss": 1.4130859375,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.07142857142857142,
42
+ "grad_norm": 0.14219045639038086,
43
+ "learning_rate": 5.714285714285714e-05,
44
+ "loss": 1.37109375,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.08571428571428572,
49
+ "grad_norm": 0.110666424036026,
50
+ "learning_rate": 7.142857142857143e-05,
51
+ "loss": 1.2802734375,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.1,
56
+ "grad_norm": 0.07214633375406265,
57
+ "learning_rate": 8.571428571428571e-05,
58
+ "loss": 1.236328125,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.11428571428571428,
63
+ "grad_norm": 0.09853629767894745,
64
+ "learning_rate": 0.0001,
65
+ "loss": 1.21240234375,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.12857142857142856,
70
+ "grad_norm": 0.09580913931131363,
71
+ "learning_rate": 9.999461133085083e-05,
72
+ "loss": 1.1611328125,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.14285714285714285,
77
+ "grad_norm": 0.10751494020223618,
78
+ "learning_rate": 9.997844661397017e-05,
79
+ "loss": 1.1689453125,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.15714285714285714,
84
+ "grad_norm": 0.09434256702661514,
85
+ "learning_rate": 9.995150972074965e-05,
86
+ "loss": 1.14892578125,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.17142857142857143,
91
+ "grad_norm": 0.10388778895139694,
92
+ "learning_rate": 9.99138071024784e-05,
93
+ "loss": 1.11669921875,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.18571428571428572,
98
+ "grad_norm": 0.06100620701909065,
99
+ "learning_rate": 9.986534778879803e-05,
100
+ "loss": 1.0830078125,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.2,
105
+ "grad_norm": 0.05543210357427597,
106
+ "learning_rate": 9.980614338554001e-05,
107
+ "loss": 1.0673828125,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.21428571428571427,
112
+ "grad_norm": 0.05129709094762802,
113
+ "learning_rate": 9.97362080719462e-05,
114
+ "loss": 1.03955078125,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.22857142857142856,
119
+ "grad_norm": 0.05103077366948128,
120
+ "learning_rate": 9.965555859727286e-05,
121
+ "loss": 1.04150390625,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.24285714285714285,
126
+ "grad_norm": 0.05306376516819,
127
+ "learning_rate": 9.956421427677942e-05,
128
+ "loss": 0.9921875,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.2571428571428571,
133
+ "grad_norm": 0.0529288649559021,
134
+ "learning_rate": 9.946219698710239e-05,
135
+ "loss": 0.98974609375,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.2714285714285714,
140
+ "grad_norm": 0.05011645331978798,
141
+ "learning_rate": 9.934953116101605e-05,
142
+ "loss": 0.970703125,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.2857142857142857,
147
+ "grad_norm": 0.04930735006928444,
148
+ "learning_rate": 9.92262437815809e-05,
149
+ "loss": 0.96923828125,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.3,
154
+ "grad_norm": 0.045997343957424164,
155
+ "learning_rate": 9.909236437568131e-05,
156
+ "loss": 0.95654296875,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.3142857142857143,
161
+ "grad_norm": 0.0459485799074173,
162
+ "learning_rate": 9.89479250069539e-05,
163
+ "loss": 0.962890625,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.32857142857142857,
168
+ "grad_norm": 0.05136457830667496,
169
+ "learning_rate": 9.879296026810846e-05,
170
+ "loss": 0.9443359375,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.34285714285714286,
175
+ "grad_norm": 0.05191263556480408,
176
+ "learning_rate": 9.862750727264311e-05,
177
+ "loss": 0.9482421875,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.35714285714285715,
182
+ "grad_norm": 0.045134589076042175,
183
+ "learning_rate": 9.845160564595573e-05,
184
+ "loss": 0.92578125,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.37142857142857144,
189
+ "grad_norm": 0.044029735028743744,
190
+ "learning_rate": 9.826529751585381e-05,
191
+ "loss": 0.91943359375,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.38571428571428573,
196
+ "grad_norm": 0.052899908274412155,
197
+ "learning_rate": 9.806862750246505e-05,
198
+ "loss": 0.9345703125,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.4,
203
+ "grad_norm": 0.04427888244390488,
204
+ "learning_rate": 9.786164270755095e-05,
205
+ "loss": 0.88037109375,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.4142857142857143,
210
+ "grad_norm": 0.04433929920196533,
211
+ "learning_rate": 9.764439270322611e-05,
212
+ "loss": 0.90380859375,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.42857142857142855,
217
+ "grad_norm": 0.04645824059844017,
218
+ "learning_rate": 9.741692952008592e-05,
219
+ "loss": 0.87646484375,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.44285714285714284,
224
+ "grad_norm": 0.04405355453491211,
225
+ "learning_rate": 9.717930763474537e-05,
226
+ "loss": 0.916015625,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.45714285714285713,
231
+ "grad_norm": 0.05218774825334549,
232
+ "learning_rate": 9.693158395679215e-05,
233
+ "loss": 0.8779296875,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.4714285714285714,
238
+ "grad_norm": 0.042239945381879807,
239
+ "learning_rate": 9.667381781515695e-05,
240
+ "loss": 0.8681640625,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.4857142857142857,
245
+ "grad_norm": 0.04367329180240631,
246
+ "learning_rate": 9.640607094390445e-05,
247
+ "loss": 0.85595703125,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.5,
252
+ "grad_norm": 0.04941326379776001,
253
+ "learning_rate": 9.61284074674482e-05,
254
+ "loss": 0.8779296875,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.5142857142857142,
259
+ "grad_norm": 0.052676014602184296,
260
+ "learning_rate": 9.584089388519307e-05,
261
+ "loss": 0.84716796875,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.5285714285714286,
266
+ "grad_norm": 0.04546784237027168,
267
+ "learning_rate": 9.554359905560886e-05,
268
+ "loss": 0.84716796875,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.5428571428571428,
273
+ "grad_norm": 0.04700865596532822,
274
+ "learning_rate": 9.523659417973897e-05,
275
+ "loss": 0.8603515625,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.5571428571428572,
280
+ "grad_norm": 0.04255075752735138,
281
+ "learning_rate": 9.4919952784148e-05,
282
+ "loss": 0.83642578125,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.5714285714285714,
287
+ "grad_norm": 0.04506116360425949,
288
+ "learning_rate": 9.459375070331236e-05,
289
+ "loss": 0.8408203125,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.5857142857142857,
294
+ "grad_norm": 0.044488076120615005,
295
+ "learning_rate": 9.425806606145826e-05,
296
+ "loss": 0.841796875,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.6,
301
+ "grad_norm": 0.04531097412109375,
302
+ "learning_rate": 9.391297925385118e-05,
303
+ "loss": 0.83740234375,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.6,
308
+ "eval_loss": 0.823486328125,
309
+ "eval_runtime": 12.7198,
310
+ "eval_samples_per_second": 0.786,
311
+ "eval_steps_per_second": 0.157,
312
+ "step": 42
313
+ },
314
+ {
315
+ "epoch": 0.6142857142857143,
316
+ "grad_norm": 0.04757943004369736,
317
+ "learning_rate": 9.355857292754152e-05,
318
+ "loss": 0.8017578125,
319
+ "step": 43
320
+ },
321
+ {
322
+ "epoch": 0.6285714285714286,
323
+ "grad_norm": 0.046234458684921265,
324
+ "learning_rate": 9.319493196157092e-05,
325
+ "loss": 0.818359375,
326
+ "step": 44
327
+ },
328
+ {
329
+ "epoch": 0.6428571428571429,
330
+ "grad_norm": 0.04600878804922104,
331
+ "learning_rate": 9.282214344664404e-05,
332
+ "loss": 0.81640625,
333
+ "step": 45
334
+ },
335
+ {
336
+ "epoch": 0.6571428571428571,
337
+ "grad_norm": 0.07235831022262573,
338
+ "learning_rate": 9.244029666427061e-05,
339
+ "loss": 0.818359375,
340
+ "step": 46
341
+ },
342
+ {
343
+ "epoch": 0.6714285714285714,
344
+ "grad_norm": 0.04685613512992859,
345
+ "learning_rate": 9.204948306538293e-05,
346
+ "loss": 0.84521484375,
347
+ "step": 47
348
+ },
349
+ {
350
+ "epoch": 0.6857142857142857,
351
+ "grad_norm": 0.04504545032978058,
352
+ "learning_rate": 9.164979624843358e-05,
353
+ "loss": 0.806640625,
354
+ "step": 48
355
+ },
356
+ {
357
+ "epoch": 0.7,
358
+ "grad_norm": 0.04681597277522087,
359
+ "learning_rate": 9.124133193697898e-05,
360
+ "loss": 0.80126953125,
361
+ "step": 49
362
+ },
363
+ {
364
+ "epoch": 0.7142857142857143,
365
+ "grad_norm": 0.049921900033950806,
366
+ "learning_rate": 9.082418795675397e-05,
367
+ "loss": 0.79541015625,
368
+ "step": 50
369
+ },
370
+ {
371
+ "epoch": 0.7285714285714285,
372
+ "grad_norm": 0.04480814188718796,
373
+ "learning_rate": 9.039846421224288e-05,
374
+ "loss": 0.7666015625,
375
+ "step": 51
376
+ },
377
+ {
378
+ "epoch": 0.7428571428571429,
379
+ "grad_norm": 0.048868753015995026,
380
+ "learning_rate": 8.996426266275271e-05,
381
+ "loss": 0.80615234375,
382
+ "step": 52
383
+ },
384
+ {
385
+ "epoch": 0.7571428571428571,
386
+ "grad_norm": 0.04697711020708084,
387
+ "learning_rate": 8.952168729799435e-05,
388
+ "loss": 0.787109375,
389
+ "step": 53
390
+ },
391
+ {
392
+ "epoch": 0.7714285714285715,
393
+ "grad_norm": 0.0476866252720356,
394
+ "learning_rate": 8.90708441131773e-05,
395
+ "loss": 0.7880859375,
396
+ "step": 54
397
+ },
398
+ {
399
+ "epoch": 0.7857142857142857,
400
+ "grad_norm": 0.047018349170684814,
401
+ "learning_rate": 8.861184108362425e-05,
402
+ "loss": 0.77880859375,
403
+ "step": 55
404
+ },
405
+ {
406
+ "epoch": 0.8,
407
+ "grad_norm": 0.05050313100218773,
408
+ "learning_rate": 8.814478813891148e-05,
409
+ "loss": 0.76953125,
410
+ "step": 56
411
+ },
412
+ {
413
+ "epoch": 0.8142857142857143,
414
+ "grad_norm": 0.049961939454078674,
415
+ "learning_rate": 8.766979713654089e-05,
416
+ "loss": 0.794921875,
417
+ "step": 57
418
+ },
419
+ {
420
+ "epoch": 0.8285714285714286,
421
+ "grad_norm": 0.04898722842335701,
422
+ "learning_rate": 8.718698183515077e-05,
423
+ "loss": 0.77880859375,
424
+ "step": 58
425
+ },
426
+ {
427
+ "epoch": 0.8428571428571429,
428
+ "grad_norm": 0.05006740987300873,
429
+ "learning_rate": 8.669645786727083e-05,
430
+ "loss": 0.80419921875,
431
+ "step": 59
432
+ },
433
+ {
434
+ "epoch": 0.8571428571428571,
435
+ "grad_norm": 0.05039166659116745,
436
+ "learning_rate": 8.619834271162879e-05,
437
+ "loss": 0.7734375,
438
+ "step": 60
439
+ },
440
+ {
441
+ "epoch": 0.8714285714285714,
442
+ "grad_norm": 0.051033422350883484,
443
+ "learning_rate": 8.56927556650145e-05,
444
+ "loss": 0.755859375,
445
+ "step": 61
446
+ },
447
+ {
448
+ "epoch": 0.8857142857142857,
449
+ "grad_norm": 0.05211988091468811,
450
+ "learning_rate": 8.517981781370884e-05,
451
+ "loss": 0.77734375,
452
+ "step": 62
453
+ },
454
+ {
455
+ "epoch": 0.9,
456
+ "grad_norm": 0.04897433891892433,
457
+ "learning_rate": 8.465965200448403e-05,
458
+ "loss": 0.76904296875,
459
+ "step": 63
460
+ },
461
+ {
462
+ "epoch": 0.9142857142857143,
463
+ "grad_norm": 0.05581013858318329,
464
+ "learning_rate": 8.413238281518225e-05,
465
+ "loss": 0.77392578125,
466
+ "step": 64
467
+ },
468
+ {
469
+ "epoch": 0.9285714285714286,
470
+ "grad_norm": 0.05405630171298981,
471
+ "learning_rate": 8.359813652487964e-05,
472
+ "loss": 0.7724609375,
473
+ "step": 65
474
+ },
475
+ {
476
+ "epoch": 0.9428571428571428,
477
+ "grad_norm": 0.07353562116622925,
478
+ "learning_rate": 8.305704108364301e-05,
479
+ "loss": 0.77197265625,
480
+ "step": 66
481
+ },
482
+ {
483
+ "epoch": 0.9571428571428572,
484
+ "grad_norm": 0.05411151796579361,
485
+ "learning_rate": 8.250922608188617e-05,
486
+ "loss": 0.7568359375,
487
+ "step": 67
488
+ },
489
+ {
490
+ "epoch": 0.9714285714285714,
491
+ "grad_norm": 0.052922919392585754,
492
+ "learning_rate": 8.195482271933352e-05,
493
+ "loss": 0.748046875,
494
+ "step": 68
495
+ },
496
+ {
497
+ "epoch": 0.9857142857142858,
498
+ "grad_norm": 0.054411035031080246,
499
+ "learning_rate": 8.139396377359824e-05,
500
+ "loss": 0.76025390625,
501
+ "step": 69
502
+ },
503
+ {
504
+ "epoch": 1.0,
505
+ "grad_norm": 0.053164735436439514,
506
+ "learning_rate": 8.082678356838245e-05,
507
+ "loss": 0.734375,
508
+ "step": 70
509
+ },
510
+ {
511
+ "epoch": 1.0142857142857142,
512
+ "grad_norm": 0.05180563032627106,
513
+ "learning_rate": 8.025341794130722e-05,
514
+ "loss": 0.7333984375,
515
+ "step": 71
516
+ },
517
+ {
518
+ "epoch": 1.0285714285714285,
519
+ "grad_norm": 0.06838234513998032,
520
+ "learning_rate": 7.96740042113799e-05,
521
+ "loss": 0.75927734375,
522
+ "step": 72
523
+ },
524
+ {
525
+ "epoch": 1.042857142857143,
526
+ "grad_norm": 0.051840752363204956,
527
+ "learning_rate": 7.908868114610677e-05,
528
+ "loss": 0.71728515625,
529
+ "step": 73
530
+ },
531
+ {
532
+ "epoch": 1.0571428571428572,
533
+ "grad_norm": 0.055688485503196716,
534
+ "learning_rate": 7.849758892825868e-05,
535
+ "loss": 0.74755859375,
536
+ "step": 74
537
+ },
538
+ {
539
+ "epoch": 1.0714285714285714,
540
+ "grad_norm": 0.05514116212725639,
541
+ "learning_rate": 7.790086912229781e-05,
542
+ "loss": 0.76904296875,
543
+ "step": 75
544
+ },
545
+ {
546
+ "epoch": 1.0857142857142856,
547
+ "grad_norm": 0.06220082938671112,
548
+ "learning_rate": 7.729866464047343e-05,
549
+ "loss": 0.7509765625,
550
+ "step": 76
551
+ },
552
+ {
553
+ "epoch": 1.1,
554
+ "grad_norm": 0.055815357714891434,
555
+ "learning_rate": 7.6691119708595e-05,
556
+ "loss": 0.7529296875,
557
+ "step": 77
558
+ },
559
+ {
560
+ "epoch": 1.1142857142857143,
561
+ "grad_norm": 0.06340858340263367,
562
+ "learning_rate": 7.607837983149056e-05,
563
+ "loss": 0.7509765625,
564
+ "step": 78
565
+ },
566
+ {
567
+ "epoch": 1.1285714285714286,
568
+ "grad_norm": 0.05273920297622681,
569
+ "learning_rate": 7.54605917581589e-05,
570
+ "loss": 0.7373046875,
571
+ "step": 79
572
+ },
573
+ {
574
+ "epoch": 1.1428571428571428,
575
+ "grad_norm": 0.060172632336616516,
576
+ "learning_rate": 7.483790344662363e-05,
577
+ "loss": 0.73876953125,
578
+ "step": 80
579
+ },
580
+ {
581
+ "epoch": 1.157142857142857,
582
+ "grad_norm": 0.05791589617729187,
583
+ "learning_rate": 7.42104640284978e-05,
584
+ "loss": 0.75341796875,
585
+ "step": 81
586
+ },
587
+ {
588
+ "epoch": 1.1714285714285715,
589
+ "grad_norm": 0.053483158349990845,
590
+ "learning_rate": 7.357842377326747e-05,
591
+ "loss": 0.75390625,
592
+ "step": 82
593
+ },
594
+ {
595
+ "epoch": 1.1857142857142857,
596
+ "grad_norm": 0.05703427270054817,
597
+ "learning_rate": 7.294193405230255e-05,
598
+ "loss": 0.736328125,
599
+ "step": 83
600
+ },
601
+ {
602
+ "epoch": 1.2,
603
+ "grad_norm": 0.05676823481917381,
604
+ "learning_rate": 7.230114730260413e-05,
605
+ "loss": 0.74853515625,
606
+ "step": 84
607
+ },
608
+ {
609
+ "epoch": 1.2,
610
+ "eval_loss": 0.7371826171875,
611
+ "eval_runtime": 12.6958,
612
+ "eval_samples_per_second": 0.788,
613
+ "eval_steps_per_second": 0.158,
614
+ "step": 84
615
+ },
616
+ {
617
+ "epoch": 1.2142857142857142,
618
+ "grad_norm": 0.05460375174880028,
619
+ "learning_rate": 7.165621699029615e-05,
620
+ "loss": 0.7294921875,
621
+ "step": 85
622
+ },
623
+ {
624
+ "epoch": 1.2285714285714286,
625
+ "grad_norm": 0.058347344398498535,
626
+ "learning_rate": 7.100729757387093e-05,
627
+ "loss": 0.74560546875,
628
+ "step": 86
629
+ },
630
+ {
631
+ "epoch": 1.2428571428571429,
632
+ "grad_norm": 0.05723877623677254,
633
+ "learning_rate": 7.03545444671969e-05,
634
+ "loss": 0.70263671875,
635
+ "step": 87
636
+ },
637
+ {
638
+ "epoch": 1.2571428571428571,
639
+ "grad_norm": 0.05612649396061897,
640
+ "learning_rate": 6.969811400229756e-05,
641
+ "loss": 0.71240234375,
642
+ "step": 88
643
+ },
644
+ {
645
+ "epoch": 1.2714285714285714,
646
+ "grad_norm": 0.05999016389250755,
647
+ "learning_rate": 6.90381633919104e-05,
648
+ "loss": 0.7080078125,
649
+ "step": 89
650
+ },
651
+ {
652
+ "epoch": 1.2857142857142856,
653
+ "grad_norm": 0.055943626910448074,
654
+ "learning_rate": 6.837485069183519e-05,
655
+ "loss": 0.708984375,
656
+ "step": 90
657
+ },
658
+ {
659
+ "epoch": 1.3,
660
+ "grad_norm": 0.05445539951324463,
661
+ "learning_rate": 6.770833476308007e-05,
662
+ "loss": 0.71484375,
663
+ "step": 91
664
+ },
665
+ {
666
+ "epoch": 1.3142857142857143,
667
+ "grad_norm": 0.05527206137776375,
668
+ "learning_rate": 6.703877523381496e-05,
669
+ "loss": 0.732421875,
670
+ "step": 92
671
+ },
672
+ {
673
+ "epoch": 1.3285714285714285,
674
+ "grad_norm": 0.054216012358665466,
675
+ "learning_rate": 6.636633246114108e-05,
676
+ "loss": 0.71142578125,
677
+ "step": 93
678
+ },
679
+ {
680
+ "epoch": 1.342857142857143,
681
+ "grad_norm": 0.058076757937669754,
682
+ "learning_rate": 6.569116749268622e-05,
683
+ "loss": 0.7333984375,
684
+ "step": 94
685
+ },
686
+ {
687
+ "epoch": 1.3571428571428572,
688
+ "grad_norm": 0.056523364037275314,
689
+ "learning_rate": 6.501344202803414e-05,
690
+ "loss": 0.716796875,
691
+ "step": 95
692
+ },
693
+ {
694
+ "epoch": 1.3714285714285714,
695
+ "grad_norm": 0.05528922751545906,
696
+ "learning_rate": 6.433331837999837e-05,
697
+ "loss": 0.71484375,
698
+ "step": 96
699
+ },
700
+ {
701
+ "epoch": 1.3857142857142857,
702
+ "grad_norm": 0.06398510187864304,
703
+ "learning_rate": 6.365095943574866e-05,
704
+ "loss": 0.73193359375,
705
+ "step": 97
706
+ },
707
+ {
708
+ "epoch": 1.4,
709
+ "grad_norm": 0.058720558881759644,
710
+ "learning_rate": 6.296652861780017e-05,
711
+ "loss": 0.68994140625,
712
+ "step": 98
713
+ },
714
+ {
715
+ "epoch": 1.4142857142857144,
716
+ "grad_norm": 0.055224865674972534,
717
+ "learning_rate": 6.228018984487442e-05,
718
+ "loss": 0.72314453125,
719
+ "step": 99
720
+ },
721
+ {
722
+ "epoch": 1.4285714285714286,
723
+ "grad_norm": 0.05576997250318527,
724
+ "learning_rate": 6.159210749264121e-05,
725
+ "loss": 0.6953125,
726
+ "step": 100
727
+ },
728
+ {
729
+ "epoch": 1.4428571428571428,
730
+ "grad_norm": 0.06290734559297562,
731
+ "learning_rate": 6.09024463543514e-05,
732
+ "loss": 0.736328125,
733
+ "step": 101
734
+ },
735
+ {
736
+ "epoch": 1.457142857142857,
737
+ "grad_norm": 0.05929115042090416,
738
+ "learning_rate": 6.02113716013694e-05,
739
+ "loss": 0.69775390625,
740
+ "step": 102
741
+ },
742
+ {
743
+ "epoch": 1.4714285714285715,
744
+ "grad_norm": 0.056523021310567856,
745
+ "learning_rate": 5.951904874361527e-05,
746
+ "loss": 0.70263671875,
747
+ "step": 103
748
+ },
749
+ {
750
+ "epoch": 1.4857142857142858,
751
+ "grad_norm": 0.06137212738394737,
752
+ "learning_rate": 5.8825643589925636e-05,
753
+ "loss": 0.6923828125,
754
+ "step": 104
755
+ },
756
+ {
757
+ "epoch": 1.5,
758
+ "grad_norm": 0.05514180287718773,
759
+ "learning_rate": 5.8131322208343166e-05,
760
+ "loss": 0.71875,
761
+ "step": 105
762
+ },
763
+ {
764
+ "epoch": 1.5142857142857142,
765
+ "grad_norm": 0.06357347965240479,
766
+ "learning_rate": 5.74362508863438e-05,
767
+ "loss": 0.685302734375,
768
+ "step": 106
769
+ },
770
+ {
771
+ "epoch": 1.5285714285714285,
772
+ "grad_norm": 0.07104372978210449,
773
+ "learning_rate": 5.67405960910115e-05,
774
+ "loss": 0.6875,
775
+ "step": 107
776
+ },
777
+ {
778
+ "epoch": 1.5428571428571427,
779
+ "grad_norm": 0.06608453392982483,
780
+ "learning_rate": 5.6044524429170006e-05,
781
+ "loss": 0.7060546875,
782
+ "step": 108
783
+ },
784
+ {
785
+ "epoch": 1.5571428571428572,
786
+ "grad_norm": 0.056561872363090515,
787
+ "learning_rate": 5.5348202607481105e-05,
788
+ "loss": 0.69287109375,
789
+ "step": 109
790
+ },
791
+ {
792
+ "epoch": 1.5714285714285714,
793
+ "grad_norm": 0.056340012699365616,
794
+ "learning_rate": 5.465179739251891e-05,
795
+ "loss": 0.69189453125,
796
+ "step": 110
797
+ },
798
+ {
799
+ "epoch": 1.5857142857142859,
800
+ "grad_norm": 0.05912540853023529,
801
+ "learning_rate": 5.395547557082999e-05,
802
+ "loss": 0.70068359375,
803
+ "step": 111
804
+ },
805
+ {
806
+ "epoch": 1.6,
807
+ "grad_norm": 0.06018223986029625,
808
+ "learning_rate": 5.32594039089885e-05,
809
+ "loss": 0.69921875,
810
+ "step": 112
811
+ },
812
+ {
813
+ "epoch": 1.6142857142857143,
814
+ "grad_norm": 0.0592244416475296,
815
+ "learning_rate": 5.2563749113656216e-05,
816
+ "loss": 0.667236328125,
817
+ "step": 113
818
+ },
819
+ {
820
+ "epoch": 1.6285714285714286,
821
+ "grad_norm": 0.05921940505504608,
822
+ "learning_rate": 5.186867779165685e-05,
823
+ "loss": 0.6845703125,
824
+ "step": 114
825
+ },
826
+ {
827
+ "epoch": 1.6428571428571428,
828
+ "grad_norm": 0.061107177287340164,
829
+ "learning_rate": 5.117435641007439e-05,
830
+ "loss": 0.6865234375,
831
+ "step": 115
832
+ },
833
+ {
834
+ "epoch": 1.657142857142857,
835
+ "grad_norm": 0.0601227767765522,
836
+ "learning_rate": 5.048095125638474e-05,
837
+ "loss": 0.69091796875,
838
+ "step": 116
839
+ },
840
+ {
841
+ "epoch": 1.6714285714285713,
842
+ "grad_norm": 0.06221635267138481,
843
+ "learning_rate": 4.978862839863061e-05,
844
+ "loss": 0.71923828125,
845
+ "step": 117
846
+ },
847
+ {
848
+ "epoch": 1.6857142857142857,
849
+ "grad_norm": 0.062171511352062225,
850
+ "learning_rate": 4.9097553645648594e-05,
851
+ "loss": 0.68408203125,
852
+ "step": 118
853
+ },
854
+ {
855
+ "epoch": 1.7,
856
+ "grad_norm": 0.06688631325960159,
857
+ "learning_rate": 4.840789250735879e-05,
858
+ "loss": 0.685546875,
859
+ "step": 119
860
+ },
861
+ {
862
+ "epoch": 1.7142857142857144,
863
+ "grad_norm": 0.062123820185661316,
864
+ "learning_rate": 4.771981015512559e-05,
865
+ "loss": 0.67529296875,
866
+ "step": 120
867
+ },
868
+ {
869
+ "epoch": 1.7285714285714286,
870
+ "grad_norm": 0.059517137706279755,
871
+ "learning_rate": 4.7033471382199836e-05,
872
+ "loss": 0.65283203125,
873
+ "step": 121
874
+ },
875
+ {
876
+ "epoch": 1.7428571428571429,
877
+ "grad_norm": 0.06246113404631615,
878
+ "learning_rate": 4.6349040564251346e-05,
879
+ "loss": 0.6943359375,
880
+ "step": 122
881
+ },
882
+ {
883
+ "epoch": 1.7571428571428571,
884
+ "grad_norm": 0.09060859680175781,
885
+ "learning_rate": 4.5666681620001625e-05,
886
+ "loss": 0.67431640625,
887
+ "step": 123
888
+ },
889
+ {
890
+ "epoch": 1.7714285714285714,
891
+ "grad_norm": 0.06127085164189339,
892
+ "learning_rate": 4.498655797196586e-05,
893
+ "loss": 0.6796875,
894
+ "step": 124
895
+ },
896
+ {
897
+ "epoch": 1.7857142857142856,
898
+ "grad_norm": 0.061497125774621964,
899
+ "learning_rate": 4.4308832507313815e-05,
900
+ "loss": 0.67431640625,
901
+ "step": 125
902
+ },
903
+ {
904
+ "epoch": 1.8,
905
+ "grad_norm": 0.06085183098912239,
906
+ "learning_rate": 4.3633667538858934e-05,
907
+ "loss": 0.6611328125,
908
+ "step": 126
909
+ },
910
+ {
911
+ "epoch": 1.8,
912
+ "eval_loss": 0.7088623046875,
913
+ "eval_runtime": 12.6903,
914
+ "eval_samples_per_second": 0.788,
915
+ "eval_steps_per_second": 0.158,
916
+ "step": 126
917
+ },
918
+ {
919
+ "epoch": 1.8142857142857143,
920
+ "grad_norm": 0.05988273769617081,
921
+ "learning_rate": 4.296122476618507e-05,
922
+ "loss": 0.689453125,
923
+ "step": 127
924
+ },
925
+ {
926
+ "epoch": 1.8285714285714287,
927
+ "grad_norm": 0.06360983848571777,
928
+ "learning_rate": 4.229166523691993e-05,
929
+ "loss": 0.673828125,
930
+ "step": 128
931
+ },
932
+ {
933
+ "epoch": 1.842857142857143,
934
+ "grad_norm": 0.06351760774850845,
935
+ "learning_rate": 4.162514930816481e-05,
936
+ "loss": 0.70068359375,
937
+ "step": 129
938
+ },
939
+ {
940
+ "epoch": 1.8571428571428572,
941
+ "grad_norm": 0.061407994478940964,
942
+ "learning_rate": 4.09618366080896e-05,
943
+ "loss": 0.673828125,
944
+ "step": 130
945
+ },
946
+ {
947
+ "epoch": 1.8714285714285714,
948
+ "grad_norm": 0.06777355074882507,
949
+ "learning_rate": 4.0301885997702457e-05,
950
+ "loss": 0.6591796875,
951
+ "step": 131
952
+ },
953
+ {
954
+ "epoch": 1.8857142857142857,
955
+ "grad_norm": 0.059942860156297684,
956
+ "learning_rate": 3.9645455532803086e-05,
957
+ "loss": 0.68310546875,
958
+ "step": 132
959
+ },
960
+ {
961
+ "epoch": 1.9,
962
+ "grad_norm": 0.06295284628868103,
963
+ "learning_rate": 3.899270242612907e-05,
964
+ "loss": 0.67333984375,
965
+ "step": 133
966
+ },
967
+ {
968
+ "epoch": 1.9142857142857141,
969
+ "grad_norm": 0.06429057568311691,
970
+ "learning_rate": 3.834378300970385e-05,
971
+ "loss": 0.6806640625,
972
+ "step": 134
973
+ },
974
+ {
975
+ "epoch": 1.9285714285714286,
976
+ "grad_norm": 0.062211379408836365,
977
+ "learning_rate": 3.7698852697395884e-05,
978
+ "loss": 0.67724609375,
979
+ "step": 135
980
+ },
981
+ {
982
+ "epoch": 1.9428571428571428,
983
+ "grad_norm": 0.0751936212182045,
984
+ "learning_rate": 3.7058065947697454e-05,
985
+ "loss": 0.6796875,
986
+ "step": 136
987
+ },
988
+ {
989
+ "epoch": 1.9571428571428573,
990
+ "grad_norm": 0.06252847611904144,
991
+ "learning_rate": 3.6421576226732544e-05,
992
+ "loss": 0.6640625,
993
+ "step": 137
994
+ },
995
+ {
996
+ "epoch": 1.9714285714285715,
997
+ "grad_norm": 0.06349719315767288,
998
+ "learning_rate": 3.57895359715022e-05,
999
+ "loss": 0.6572265625,
1000
+ "step": 138
1001
+ },
1002
+ {
1003
+ "epoch": 1.9857142857142858,
1004
+ "grad_norm": 0.06345172226428986,
1005
+ "learning_rate": 3.516209655337639e-05,
1006
+ "loss": 0.6708984375,
1007
+ "step": 139
1008
+ },
1009
+ {
1010
+ "epoch": 2.0,
1011
+ "grad_norm": 0.06399086862802505,
1012
+ "learning_rate": 3.4539408241841105e-05,
1013
+ "loss": 0.6455078125,
1014
+ "step": 140
1015
+ },
1016
+ {
1017
+ "epoch": 2.0142857142857142,
1018
+ "grad_norm": 0.06483668088912964,
1019
+ "learning_rate": 3.392162016850945e-05,
1020
+ "loss": 0.64697265625,
1021
+ "step": 141
1022
+ },
1023
+ {
1024
+ "epoch": 2.0285714285714285,
1025
+ "grad_norm": 0.06015940010547638,
1026
+ "learning_rate": 3.330888029140503e-05,
1027
+ "loss": 0.6748046875,
1028
+ "step": 142
1029
+ },
1030
+ {
1031
+ "epoch": 2.0428571428571427,
1032
+ "grad_norm": 0.06585846096277237,
1033
+ "learning_rate": 3.2701335359526584e-05,
1034
+ "loss": 0.634765625,
1035
+ "step": 143
1036
+ },
1037
+ {
1038
+ "epoch": 2.057142857142857,
1039
+ "grad_norm": 0.06796801090240479,
1040
+ "learning_rate": 3.209913087770221e-05,
1041
+ "loss": 0.66357421875,
1042
+ "step": 144
1043
+ },
1044
+ {
1045
+ "epoch": 2.0714285714285716,
1046
+ "grad_norm": 0.06410115957260132,
1047
+ "learning_rate": 3.1502411071741334e-05,
1048
+ "loss": 0.68408203125,
1049
+ "step": 145
1050
+ },
1051
+ {
1052
+ "epoch": 2.085714285714286,
1053
+ "grad_norm": 0.07315430790185928,
1054
+ "learning_rate": 3.091131885389324e-05,
1055
+ "loss": 0.66943359375,
1056
+ "step": 146
1057
+ },
1058
+ {
1059
+ "epoch": 2.1,
1060
+ "grad_norm": 0.06741099804639816,
1061
+ "learning_rate": 3.032599578862011e-05,
1062
+ "loss": 0.67236328125,
1063
+ "step": 147
1064
+ },
1065
+ {
1066
+ "epoch": 2.1142857142857143,
1067
+ "grad_norm": 0.06903790682554245,
1068
+ "learning_rate": 2.97465820586928e-05,
1069
+ "loss": 0.66845703125,
1070
+ "step": 148
1071
+ },
1072
+ {
1073
+ "epoch": 2.1285714285714286,
1074
+ "grad_norm": 0.06851155310869217,
1075
+ "learning_rate": 2.9173216431617545e-05,
1076
+ "loss": 0.66162109375,
1077
+ "step": 149
1078
+ },
1079
+ {
1080
+ "epoch": 2.142857142857143,
1081
+ "grad_norm": 0.06491309404373169,
1082
+ "learning_rate": 2.8606036226401768e-05,
1083
+ "loss": 0.65966796875,
1084
+ "step": 150
1085
+ },
1086
+ {
1087
+ "epoch": 2.157142857142857,
1088
+ "grad_norm": 0.06776642799377441,
1089
+ "learning_rate": 2.804517728066649e-05,
1090
+ "loss": 0.6748046875,
1091
+ "step": 151
1092
+ },
1093
+ {
1094
+ "epoch": 2.1714285714285713,
1095
+ "grad_norm": 0.06124527007341385,
1096
+ "learning_rate": 2.749077391811384e-05,
1097
+ "loss": 0.67822265625,
1098
+ "step": 152
1099
+ },
1100
+ {
1101
+ "epoch": 2.185714285714286,
1102
+ "grad_norm": 0.06878867745399475,
1103
+ "learning_rate": 2.6942958916356998e-05,
1104
+ "loss": 0.662109375,
1105
+ "step": 153
1106
+ },
1107
+ {
1108
+ "epoch": 2.2,
1109
+ "grad_norm": 0.06806619465351105,
1110
+ "learning_rate": 2.640186347512037e-05,
1111
+ "loss": 0.671875,
1112
+ "step": 154
1113
+ },
1114
+ {
1115
+ "epoch": 2.2142857142857144,
1116
+ "grad_norm": 0.06395353376865387,
1117
+ "learning_rate": 2.586761718481776e-05,
1118
+ "loss": 0.65576171875,
1119
+ "step": 155
1120
+ },
1121
+ {
1122
+ "epoch": 2.2285714285714286,
1123
+ "grad_norm": 0.07178875803947449,
1124
+ "learning_rate": 2.5340347995515977e-05,
1125
+ "loss": 0.67138671875,
1126
+ "step": 156
1127
+ },
1128
+ {
1129
+ "epoch": 2.242857142857143,
1130
+ "grad_norm": 0.06459272652864456,
1131
+ "learning_rate": 2.4820182186291172e-05,
1132
+ "loss": 0.63134765625,
1133
+ "step": 157
1134
+ },
1135
+ {
1136
+ "epoch": 2.257142857142857,
1137
+ "grad_norm": 0.06613647937774658,
1138
+ "learning_rate": 2.430724433498552e-05,
1139
+ "loss": 0.64111328125,
1140
+ "step": 158
1141
+ },
1142
+ {
1143
+ "epoch": 2.2714285714285714,
1144
+ "grad_norm": 0.06713347882032394,
1145
+ "learning_rate": 2.3801657288371217e-05,
1146
+ "loss": 0.63916015625,
1147
+ "step": 159
1148
+ },
1149
+ {
1150
+ "epoch": 2.2857142857142856,
1151
+ "grad_norm": 0.06648610532283783,
1152
+ "learning_rate": 2.3303542132729168e-05,
1153
+ "loss": 0.638671875,
1154
+ "step": 160
1155
+ },
1156
+ {
1157
+ "epoch": 2.3,
1158
+ "grad_norm": 0.06578565388917923,
1159
+ "learning_rate": 2.281301816484925e-05,
1160
+ "loss": 0.6474609375,
1161
+ "step": 161
1162
+ },
1163
+ {
1164
+ "epoch": 2.314285714285714,
1165
+ "grad_norm": 0.0631573498249054,
1166
+ "learning_rate": 2.2330202863459122e-05,
1167
+ "loss": 0.6640625,
1168
+ "step": 162
1169
+ },
1170
+ {
1171
+ "epoch": 2.3285714285714287,
1172
+ "grad_norm": 0.06323499232530594,
1173
+ "learning_rate": 2.1855211861088538e-05,
1174
+ "loss": 0.643798828125,
1175
+ "step": 163
1176
+ },
1177
+ {
1178
+ "epoch": 2.342857142857143,
1179
+ "grad_norm": 0.06487427651882172,
1180
+ "learning_rate": 2.1388158916375755e-05,
1181
+ "loss": 0.66552734375,
1182
+ "step": 164
1183
+ },
1184
+ {
1185
+ "epoch": 2.357142857142857,
1186
+ "grad_norm": 0.06590575724840164,
1187
+ "learning_rate": 2.0929155886822716e-05,
1188
+ "loss": 0.6513671875,
1189
+ "step": 165
1190
+ },
1191
+ {
1192
+ "epoch": 2.3714285714285714,
1193
+ "grad_norm": 0.06528814882040024,
1194
+ "learning_rate": 2.0478312702005653e-05,
1195
+ "loss": 0.65087890625,
1196
+ "step": 166
1197
+ },
1198
+ {
1199
+ "epoch": 2.3857142857142857,
1200
+ "grad_norm": 0.06810116022825241,
1201
+ "learning_rate": 2.003573733724729e-05,
1202
+ "loss": 0.662109375,
1203
+ "step": 167
1204
+ },
1205
+ {
1206
+ "epoch": 2.4,
1207
+ "grad_norm": 0.0618431381881237,
1208
+ "learning_rate": 1.9601535787757132e-05,
1209
+ "loss": 0.62939453125,
1210
+ "step": 168
1211
+ },
1212
+ {
1213
+ "epoch": 2.4,
1214
+ "eval_loss": 0.6951904296875,
1215
+ "eval_runtime": 12.6967,
1216
+ "eval_samples_per_second": 0.788,
1217
+ "eval_steps_per_second": 0.158,
1218
+ "step": 168
1219
+ },
1220
+ {
1221
+ "epoch": 2.414285714285714,
1222
+ "grad_norm": 0.06515216827392578,
1223
+ "learning_rate": 1.9175812043246033e-05,
1224
+ "loss": 0.66162109375,
1225
+ "step": 169
1226
+ },
1227
+ {
1228
+ "epoch": 2.4285714285714284,
1229
+ "grad_norm": 0.06773951649665833,
1230
+ "learning_rate": 1.8758668063021033e-05,
1231
+ "loss": 0.634765625,
1232
+ "step": 170
1233
+ },
1234
+ {
1235
+ "epoch": 2.442857142857143,
1236
+ "grad_norm": 0.06553688645362854,
1237
+ "learning_rate": 1.8350203751566436e-05,
1238
+ "loss": 0.67138671875,
1239
+ "step": 171
1240
+ },
1241
+ {
1242
+ "epoch": 2.4571428571428573,
1243
+ "grad_norm": 0.06633678823709488,
1244
+ "learning_rate": 1.7950516934617083e-05,
1245
+ "loss": 0.6357421875,
1246
+ "step": 172
1247
+ },
1248
+ {
1249
+ "epoch": 2.4714285714285715,
1250
+ "grad_norm": 0.06607075780630112,
1251
+ "learning_rate": 1.75597033357294e-05,
1252
+ "loss": 0.64306640625,
1253
+ "step": 173
1254
+ },
1255
+ {
1256
+ "epoch": 2.4857142857142858,
1257
+ "grad_norm": 0.06522510200738907,
1258
+ "learning_rate": 1.717785655335597e-05,
1259
+ "loss": 0.63232421875,
1260
+ "step": 174
1261
+ },
1262
+ {
1263
+ "epoch": 2.5,
1264
+ "grad_norm": 0.06720203161239624,
1265
+ "learning_rate": 1.680506803842909e-05,
1266
+ "loss": 0.65966796875,
1267
+ "step": 175
1268
+ },
1269
+ {
1270
+ "epoch": 2.5142857142857142,
1271
+ "grad_norm": 0.06660260260105133,
1272
+ "learning_rate": 1.6441427072458494e-05,
1273
+ "loss": 0.625732421875,
1274
+ "step": 176
1275
+ },
1276
+ {
1277
+ "epoch": 2.5285714285714285,
1278
+ "grad_norm": 0.06615811586380005,
1279
+ "learning_rate": 1.6087020746148828e-05,
1280
+ "loss": 0.6298828125,
1281
+ "step": 177
1282
+ },
1283
+ {
1284
+ "epoch": 2.5428571428571427,
1285
+ "grad_norm": 0.06593484431505203,
1286
+ "learning_rate": 1.5741933938541755e-05,
1287
+ "loss": 0.64501953125,
1288
+ "step": 178
1289
+ },
1290
+ {
1291
+ "epoch": 2.557142857142857,
1292
+ "grad_norm": 0.06653065979480743,
1293
+ "learning_rate": 1.540624929668765e-05,
1294
+ "loss": 0.63720703125,
1295
+ "step": 179
1296
+ },
1297
+ {
1298
+ "epoch": 2.571428571428571,
1299
+ "grad_norm": 0.06582722812891006,
1300
+ "learning_rate": 1.5080047215852011e-05,
1301
+ "loss": 0.63525390625,
1302
+ "step": 180
1303
+ },
1304
+ {
1305
+ "epoch": 2.585714285714286,
1306
+ "grad_norm": 0.06583766639232635,
1307
+ "learning_rate": 1.4763405820261036e-05,
1308
+ "loss": 0.64697265625,
1309
+ "step": 181
1310
+ },
1311
+ {
1312
+ "epoch": 2.6,
1313
+ "grad_norm": 0.06714893132448196,
1314
+ "learning_rate": 1.4456400944391146e-05,
1315
+ "loss": 0.6455078125,
1316
+ "step": 182
1317
+ },
1318
+ {
1319
+ "epoch": 2.6142857142857143,
1320
+ "grad_norm": 0.06695859879255295,
1321
+ "learning_rate": 1.4159106114806942e-05,
1322
+ "loss": 0.610107421875,
1323
+ "step": 183
1324
+ },
1325
+ {
1326
+ "epoch": 2.6285714285714286,
1327
+ "grad_norm": 0.06631751358509064,
1328
+ "learning_rate": 1.3871592532551805e-05,
1329
+ "loss": 0.630859375,
1330
+ "step": 184
1331
+ },
1332
+ {
1333
+ "epoch": 2.642857142857143,
1334
+ "grad_norm": 0.06531959772109985,
1335
+ "learning_rate": 1.3593929056095556e-05,
1336
+ "loss": 0.630859375,
1337
+ "step": 185
1338
+ },
1339
+ {
1340
+ "epoch": 2.657142857142857,
1341
+ "grad_norm": 0.06435287743806839,
1342
+ "learning_rate": 1.332618218484306e-05,
1343
+ "loss": 0.6396484375,
1344
+ "step": 186
1345
+ },
1346
+ {
1347
+ "epoch": 2.6714285714285713,
1348
+ "grad_norm": 0.06656572967767715,
1349
+ "learning_rate": 1.3068416043207863e-05,
1350
+ "loss": 0.66552734375,
1351
+ "step": 187
1352
+ },
1353
+ {
1354
+ "epoch": 2.685714285714286,
1355
+ "grad_norm": 0.06637463718652725,
1356
+ "learning_rate": 1.2820692365254631e-05,
1357
+ "loss": 0.6328125,
1358
+ "step": 188
1359
+ },
1360
+ {
1361
+ "epoch": 2.7,
1362
+ "grad_norm": 0.0676756501197815,
1363
+ "learning_rate": 1.2583070479914087e-05,
1364
+ "loss": 0.63427734375,
1365
+ "step": 189
1366
+ },
1367
+ {
1368
+ "epoch": 2.7142857142857144,
1369
+ "grad_norm": 0.06691654771566391,
1370
+ "learning_rate": 1.2355607296773895e-05,
1371
+ "loss": 0.6240234375,
1372
+ "step": 190
1373
+ },
1374
+ {
1375
+ "epoch": 2.7285714285714286,
1376
+ "grad_norm": 0.06870891898870468,
1377
+ "learning_rate": 1.2138357292449055e-05,
1378
+ "loss": 0.603515625,
1379
+ "step": 191
1380
+ },
1381
+ {
1382
+ "epoch": 2.742857142857143,
1383
+ "grad_norm": 0.06647045165300369,
1384
+ "learning_rate": 1.1931372497534953e-05,
1385
+ "loss": 0.6455078125,
1386
+ "step": 192
1387
+ },
1388
+ {
1389
+ "epoch": 2.757142857142857,
1390
+ "grad_norm": 0.06754187494516373,
1391
+ "learning_rate": 1.1734702484146193e-05,
1392
+ "loss": 0.6279296875,
1393
+ "step": 193
1394
+ },
1395
+ {
1396
+ "epoch": 2.7714285714285714,
1397
+ "grad_norm": 0.06615348160266876,
1398
+ "learning_rate": 1.1548394354044276e-05,
1399
+ "loss": 0.6328125,
1400
+ "step": 194
1401
+ },
1402
+ {
1403
+ "epoch": 2.7857142857142856,
1404
+ "grad_norm": 0.0676516741514206,
1405
+ "learning_rate": 1.1372492727356887e-05,
1406
+ "loss": 0.62646484375,
1407
+ "step": 195
1408
+ },
1409
+ {
1410
+ "epoch": 2.8,
1411
+ "grad_norm": 0.0679558664560318,
1412
+ "learning_rate": 1.1207039731891532e-05,
1413
+ "loss": 0.61669921875,
1414
+ "step": 196
1415
+ },
1416
+ {
1417
+ "epoch": 2.814285714285714,
1418
+ "grad_norm": 0.06910320371389389,
1419
+ "learning_rate": 1.1052074993046102e-05,
1420
+ "loss": 0.64306640625,
1421
+ "step": 197
1422
+ },
1423
+ {
1424
+ "epoch": 2.8285714285714287,
1425
+ "grad_norm": 0.069993756711483,
1426
+ "learning_rate": 1.0907635624318696e-05,
1427
+ "loss": 0.627197265625,
1428
+ "step": 198
1429
+ },
1430
+ {
1431
+ "epoch": 2.842857142857143,
1432
+ "grad_norm": 0.07021188735961914,
1433
+ "learning_rate": 1.0773756218419104e-05,
1434
+ "loss": 0.65234375,
1435
+ "step": 199
1436
+ },
1437
+ {
1438
+ "epoch": 2.857142857142857,
1439
+ "grad_norm": 0.06672544032335281,
1440
+ "learning_rate": 1.0650468838983959e-05,
1441
+ "loss": 0.63037109375,
1442
+ "step": 200
1443
+ },
1444
+ {
1445
+ "epoch": 2.8714285714285714,
1446
+ "grad_norm": 0.06757517904043198,
1447
+ "learning_rate": 1.0537803012897617e-05,
1448
+ "loss": 0.61474609375,
1449
+ "step": 201
1450
+ },
1451
+ {
1452
+ "epoch": 2.8857142857142857,
1453
+ "grad_norm": 0.06685593724250793,
1454
+ "learning_rate": 1.043578572322058e-05,
1455
+ "loss": 0.6396484375,
1456
+ "step": 202
1457
+ },
1458
+ {
1459
+ "epoch": 2.9,
1460
+ "grad_norm": 0.0702473595738411,
1461
+ "learning_rate": 1.0344441402727142e-05,
1462
+ "loss": 0.63037109375,
1463
+ "step": 203
1464
+ },
1465
+ {
1466
+ "epoch": 2.914285714285714,
1467
+ "grad_norm": 0.06869243085384369,
1468
+ "learning_rate": 1.0263791928053819e-05,
1469
+ "loss": 0.63720703125,
1470
+ "step": 204
1471
+ },
1472
+ {
1473
+ "epoch": 2.928571428571429,
1474
+ "grad_norm": 0.06895088404417038,
1475
+ "learning_rate": 1.0193856614459998e-05,
1476
+ "loss": 0.6337890625,
1477
+ "step": 205
1478
+ },
1479
+ {
1480
+ "epoch": 2.942857142857143,
1481
+ "grad_norm": 0.06920134276151657,
1482
+ "learning_rate": 1.013465221120198e-05,
1483
+ "loss": 0.638671875,
1484
+ "step": 206
1485
+ },
1486
+ {
1487
+ "epoch": 2.9571428571428573,
1488
+ "grad_norm": 0.06936103105545044,
1489
+ "learning_rate": 1.0086192897521601e-05,
1490
+ "loss": 0.6201171875,
1491
+ "step": 207
1492
+ },
1493
+ {
1494
+ "epoch": 2.9714285714285715,
1495
+ "grad_norm": 0.07043518126010895,
1496
+ "learning_rate": 1.0048490279250354e-05,
1497
+ "loss": 0.61669921875,
1498
+ "step": 208
1499
+ },
1500
+ {
1501
+ "epoch": 2.9857142857142858,
1502
+ "grad_norm": 0.06810513883829117,
1503
+ "learning_rate": 1.0021553386029838e-05,
1504
+ "loss": 0.63134765625,
1505
+ "step": 209
1506
+ },
1507
+ {
1508
+ "epoch": 3.0,
1509
+ "grad_norm": 0.06843512505292892,
1510
+ "learning_rate": 1.0005388669149184e-05,
1511
+ "loss": 0.60400390625,
1512
+ "step": 210
1513
+ },
1514
+ {
1515
+ "epoch": 3.0,
1516
+ "eval_loss": 0.6898193359375,
1517
+ "eval_runtime": 12.7056,
1518
+ "eval_samples_per_second": 0.787,
1519
+ "eval_steps_per_second": 0.157,
1520
+ "step": 210
1521
+ }
1522
+ ],
1523
+ "logging_steps": 1.0,
1524
+ "max_steps": 210,
1525
+ "num_input_tokens_seen": 0,
1526
+ "num_train_epochs": 3,
1527
+ "save_steps": 0,
1528
+ "stateful_callbacks": {
1529
+ "TrainerControl": {
1530
+ "args": {
1531
+ "should_epoch_stop": false,
1532
+ "should_evaluate": false,
1533
+ "should_log": false,
1534
+ "should_save": true,
1535
+ "should_training_stop": true
1536
+ },
1537
+ "attributes": {}
1538
+ }
1539
+ },
1540
+ "total_flos": 1.7282139802791051e+19,
1541
+ "train_batch_size": 1,
1542
+ "trial_name": null,
1543
+ "trial_params": null
1544
+ }