Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- checkpoint-459/chat_template.jinja +93 -0
- checkpoint-459/config.json +36 -0
- checkpoint-459/generation_config.json +9 -0
- checkpoint-459/model.safetensors +3 -0
- checkpoint-459/optimizer.pt +3 -0
- checkpoint-459/rng_state.pth +3 -0
- checkpoint-459/scheduler.pt +3 -0
- checkpoint-459/tokenizer.json +3 -0
- checkpoint-459/tokenizer_config.json +13 -0
- checkpoint-459/trainer_state.json +3247 -0
- checkpoint-459/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -42,3 +42,4 @@ checkpoint-2754/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 42 |
checkpoint-1148/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
checkpoint-2295/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
checkpoint-230/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 42 |
checkpoint-1148/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
checkpoint-2295/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
checkpoint-230/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
checkpoint-459/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-459/chat_template.jinja
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
{%- if strftime_now is defined %}
|
| 10 |
+
{%- set date_string = strftime_now("%d %b %Y") %}
|
| 11 |
+
{%- else %}
|
| 12 |
+
{%- set date_string = "26 Jul 2024" %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if not tools is defined %}
|
| 16 |
+
{%- set tools = none %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
|
| 19 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
| 20 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 21 |
+
{%- set system_message = messages[0]['content']|trim %}
|
| 22 |
+
{%- set messages = messages[1:] %}
|
| 23 |
+
{%- else %}
|
| 24 |
+
{%- set system_message = "" %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
|
| 27 |
+
{#- System message #}
|
| 28 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
| 29 |
+
{%- if tools is not none %}
|
| 30 |
+
{{- "Environment: ipython\n" }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
| 33 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
| 34 |
+
{%- if tools is not none and not tools_in_user_message %}
|
| 35 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
| 36 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 37 |
+
{{- "Do not use variables.\n\n" }}
|
| 38 |
+
{%- for t in tools %}
|
| 39 |
+
{{- t | tojson(indent=4) }}
|
| 40 |
+
{{- "\n\n" }}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- system_message }}
|
| 44 |
+
{{- "<|eot_id|>" }}
|
| 45 |
+
|
| 46 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
| 47 |
+
{%- if tools_in_user_message and not tools is none %}
|
| 48 |
+
{#- Extract the first user message so we can plug it in here #}
|
| 49 |
+
{%- if messages | length != 0 %}
|
| 50 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
| 51 |
+
{%- set messages = messages[1:] %}
|
| 52 |
+
{%- else %}
|
| 53 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
| 56 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
| 57 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
| 58 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 59 |
+
{{- "Do not use variables.\n\n" }}
|
| 60 |
+
{%- for t in tools %}
|
| 61 |
+
{{- t | tojson(indent=4) }}
|
| 62 |
+
{{- "\n\n" }}
|
| 63 |
+
{%- endfor %}
|
| 64 |
+
{{- first_user_message + "<|eot_id|>"}}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
|
| 67 |
+
{%- for message in messages %}
|
| 68 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
| 69 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
| 70 |
+
{%- elif 'tool_calls' in message %}
|
| 71 |
+
{%- if not message.tool_calls|length == 1 %}
|
| 72 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
| 75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 76 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
| 77 |
+
{{- '"parameters": ' }}
|
| 78 |
+
{{- tool_call.arguments | tojson }}
|
| 79 |
+
{{- "}" }}
|
| 80 |
+
{{- "<|eot_id|>" }}
|
| 81 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
| 82 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
| 83 |
+
{%- if message.content is mapping or message.content is iterable %}
|
| 84 |
+
{{- message.content | tojson }}
|
| 85 |
+
{%- else %}
|
| 86 |
+
{{- message.content }}
|
| 87 |
+
{%- endif %}
|
| 88 |
+
{{- "<|eot_id|>" }}
|
| 89 |
+
{%- endif %}
|
| 90 |
+
{%- endfor %}
|
| 91 |
+
{%- if add_generation_prompt %}
|
| 92 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
| 93 |
+
{%- endif %}
|
checkpoint-459/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 128001,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 3072,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 24,
|
| 19 |
+
"num_hidden_layers": 28,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": null,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"factor": 32.0,
|
| 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": true,
|
| 33 |
+
"transformers_version": "5.4.0",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"vocab_size": 156940
|
| 36 |
+
}
|
checkpoint-459/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128001,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.9,
|
| 8 |
+
"transformers_version": "5.4.0"
|
| 9 |
+
}
|
checkpoint-459/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e78166a80b4fd6672b715948c3abbfb59e312307d26f1592e801e0edd02fc8b
|
| 3 |
+
size 13203497664
|
checkpoint-459/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c289262a70ab52a825b81831aa8f9bf0637d28ef9209d0b60342a0296999ac54
|
| 3 |
+
size 26407163507
|
checkpoint-459/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
+
size 14645
|
checkpoint-459/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:428434791f231d025440c0b52c9dc6092bc9af812cd17a0b4607cff8527e92ce
|
| 3 |
+
size 1465
|
checkpoint-459/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc3fecb199b4170636dbfab986d25f628157268d37b861f9cadaca60b1353bce
|
| 3 |
+
size 22849547
|
checkpoint-459/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"model_input_names": [
|
| 8 |
+
"input_ids",
|
| 9 |
+
"attention_mask"
|
| 10 |
+
],
|
| 11 |
+
"model_max_length": 131072,
|
| 12 |
+
"tokenizer_class": "TokenizersBackend"
|
| 13 |
+
}
|
checkpoint-459/trainer_state.json
ADDED
|
@@ -0,0 +1,3247 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 459,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.002178649237472767,
|
| 14 |
+
"grad_norm": 3.4895544052124023,
|
| 15 |
+
"learning_rate": 1e-06,
|
| 16 |
+
"loss": 4.916027545928955,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.004357298474945534,
|
| 21 |
+
"grad_norm": 4.010141372680664,
|
| 22 |
+
"learning_rate": 9.997821350762527e-07,
|
| 23 |
+
"loss": 4.920527458190918,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.006535947712418301,
|
| 28 |
+
"grad_norm": 3.5525588989257812,
|
| 29 |
+
"learning_rate": 9.995642701525054e-07,
|
| 30 |
+
"loss": 5.006848335266113,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.008714596949891068,
|
| 35 |
+
"grad_norm": 3.3555800914764404,
|
| 36 |
+
"learning_rate": 9.993464052287582e-07,
|
| 37 |
+
"loss": 4.70272159576416,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.010893246187363835,
|
| 42 |
+
"grad_norm": 2.975907564163208,
|
| 43 |
+
"learning_rate": 9.991285403050107e-07,
|
| 44 |
+
"loss": 4.784679889678955,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.013071895424836602,
|
| 49 |
+
"grad_norm": 2.828676223754883,
|
| 50 |
+
"learning_rate": 9.989106753812637e-07,
|
| 51 |
+
"loss": 4.812711715698242,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.015250544662309368,
|
| 56 |
+
"grad_norm": 3.008113384246826,
|
| 57 |
+
"learning_rate": 9.986928104575162e-07,
|
| 58 |
+
"loss": 4.691270351409912,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.017429193899782137,
|
| 63 |
+
"grad_norm": 3.6902308464050293,
|
| 64 |
+
"learning_rate": 9.98474945533769e-07,
|
| 65 |
+
"loss": 5.013348579406738,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0196078431372549,
|
| 70 |
+
"grad_norm": 2.7047119140625,
|
| 71 |
+
"learning_rate": 9.982570806100217e-07,
|
| 72 |
+
"loss": 4.6715989112854,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.02178649237472767,
|
| 77 |
+
"grad_norm": 2.4177377223968506,
|
| 78 |
+
"learning_rate": 9.980392156862744e-07,
|
| 79 |
+
"loss": 4.580904006958008,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.023965141612200435,
|
| 84 |
+
"grad_norm": 2.6055257320404053,
|
| 85 |
+
"learning_rate": 9.978213507625272e-07,
|
| 86 |
+
"loss": 4.5385613441467285,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.026143790849673203,
|
| 91 |
+
"grad_norm": 2.2186083793640137,
|
| 92 |
+
"learning_rate": 9.9760348583878e-07,
|
| 93 |
+
"loss": 4.605264663696289,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.02832244008714597,
|
| 98 |
+
"grad_norm": 3.1009016036987305,
|
| 99 |
+
"learning_rate": 9.973856209150327e-07,
|
| 100 |
+
"loss": 4.743993282318115,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.030501089324618737,
|
| 105 |
+
"grad_norm": 2.4467430114746094,
|
| 106 |
+
"learning_rate": 9.971677559912854e-07,
|
| 107 |
+
"loss": 4.731149673461914,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.032679738562091505,
|
| 112 |
+
"grad_norm": 3.1184093952178955,
|
| 113 |
+
"learning_rate": 9.969498910675381e-07,
|
| 114 |
+
"loss": 4.623490810394287,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.034858387799564274,
|
| 119 |
+
"grad_norm": 2.540374994277954,
|
| 120 |
+
"learning_rate": 9.967320261437909e-07,
|
| 121 |
+
"loss": 4.740448474884033,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.037037037037037035,
|
| 126 |
+
"grad_norm": 2.5037412643432617,
|
| 127 |
+
"learning_rate": 9.965141612200434e-07,
|
| 128 |
+
"loss": 4.6794538497924805,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0392156862745098,
|
| 133 |
+
"grad_norm": 2.528285264968872,
|
| 134 |
+
"learning_rate": 9.962962962962964e-07,
|
| 135 |
+
"loss": 4.517210483551025,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.04139433551198257,
|
| 140 |
+
"grad_norm": 2.685351610183716,
|
| 141 |
+
"learning_rate": 9.96078431372549e-07,
|
| 142 |
+
"loss": 4.633927822113037,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.04357298474945534,
|
| 147 |
+
"grad_norm": 2.660351514816284,
|
| 148 |
+
"learning_rate": 9.958605664488016e-07,
|
| 149 |
+
"loss": 4.512837886810303,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.0457516339869281,
|
| 154 |
+
"grad_norm": 2.0510494709014893,
|
| 155 |
+
"learning_rate": 9.956427015250544e-07,
|
| 156 |
+
"loss": 4.446115016937256,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.04793028322440087,
|
| 161 |
+
"grad_norm": 2.7734460830688477,
|
| 162 |
+
"learning_rate": 9.954248366013071e-07,
|
| 163 |
+
"loss": 4.655968189239502,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.05010893246187364,
|
| 168 |
+
"grad_norm": 3.266709089279175,
|
| 169 |
+
"learning_rate": 9.952069716775599e-07,
|
| 170 |
+
"loss": 4.729773044586182,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.05228758169934641,
|
| 175 |
+
"grad_norm": 3.1700313091278076,
|
| 176 |
+
"learning_rate": 9.949891067538126e-07,
|
| 177 |
+
"loss": 4.628276348114014,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.054466230936819175,
|
| 182 |
+
"grad_norm": 2.6991522312164307,
|
| 183 |
+
"learning_rate": 9.947712418300654e-07,
|
| 184 |
+
"loss": 4.719573020935059,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.05664488017429194,
|
| 189 |
+
"grad_norm": 2.118373155593872,
|
| 190 |
+
"learning_rate": 9.94553376906318e-07,
|
| 191 |
+
"loss": 4.662531852722168,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.058823529411764705,
|
| 196 |
+
"grad_norm": 2.0858867168426514,
|
| 197 |
+
"learning_rate": 9.943355119825706e-07,
|
| 198 |
+
"loss": 4.563895225524902,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.06100217864923747,
|
| 203 |
+
"grad_norm": 2.572877883911133,
|
| 204 |
+
"learning_rate": 9.941176470588236e-07,
|
| 205 |
+
"loss": 4.559572219848633,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.06318082788671024,
|
| 210 |
+
"grad_norm": 3.0945630073547363,
|
| 211 |
+
"learning_rate": 9.938997821350761e-07,
|
| 212 |
+
"loss": 4.973132610321045,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.06535947712418301,
|
| 217 |
+
"grad_norm": 2.404824733734131,
|
| 218 |
+
"learning_rate": 9.936819172113289e-07,
|
| 219 |
+
"loss": 4.668265342712402,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.06753812636165578,
|
| 224 |
+
"grad_norm": 2.565981388092041,
|
| 225 |
+
"learning_rate": 9.934640522875816e-07,
|
| 226 |
+
"loss": 4.684271335601807,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.06971677559912855,
|
| 231 |
+
"grad_norm": 2.628347635269165,
|
| 232 |
+
"learning_rate": 9.932461873638343e-07,
|
| 233 |
+
"loss": 4.641284942626953,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.0718954248366013,
|
| 238 |
+
"grad_norm": 2.4909212589263916,
|
| 239 |
+
"learning_rate": 9.93028322440087e-07,
|
| 240 |
+
"loss": 4.462052345275879,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.07407407407407407,
|
| 245 |
+
"grad_norm": 2.5438127517700195,
|
| 246 |
+
"learning_rate": 9.928104575163398e-07,
|
| 247 |
+
"loss": 4.660407543182373,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.07625272331154684,
|
| 252 |
+
"grad_norm": 2.7430713176727295,
|
| 253 |
+
"learning_rate": 9.925925925925926e-07,
|
| 254 |
+
"loss": 4.468838214874268,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.0784313725490196,
|
| 259 |
+
"grad_norm": 1.817378044128418,
|
| 260 |
+
"learning_rate": 9.923747276688453e-07,
|
| 261 |
+
"loss": 4.502563953399658,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.08061002178649238,
|
| 266 |
+
"grad_norm": 2.461793899536133,
|
| 267 |
+
"learning_rate": 9.92156862745098e-07,
|
| 268 |
+
"loss": 4.617760181427002,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.08278867102396514,
|
| 273 |
+
"grad_norm": 2.876997947692871,
|
| 274 |
+
"learning_rate": 9.919389978213508e-07,
|
| 275 |
+
"loss": 4.588554382324219,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.08496732026143791,
|
| 280 |
+
"grad_norm": 2.035167932510376,
|
| 281 |
+
"learning_rate": 9.917211328976033e-07,
|
| 282 |
+
"loss": 4.634808540344238,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.08714596949891068,
|
| 287 |
+
"grad_norm": 2.403083562850952,
|
| 288 |
+
"learning_rate": 9.915032679738563e-07,
|
| 289 |
+
"loss": 4.598034381866455,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.08932461873638345,
|
| 294 |
+
"grad_norm": 2.5495636463165283,
|
| 295 |
+
"learning_rate": 9.912854030501088e-07,
|
| 296 |
+
"loss": 4.778774738311768,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.0915032679738562,
|
| 301 |
+
"grad_norm": 3.2183687686920166,
|
| 302 |
+
"learning_rate": 9.910675381263615e-07,
|
| 303 |
+
"loss": 4.950235843658447,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.09368191721132897,
|
| 308 |
+
"grad_norm": 2.383429765701294,
|
| 309 |
+
"learning_rate": 9.908496732026143e-07,
|
| 310 |
+
"loss": 4.586299419403076,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.09586056644880174,
|
| 315 |
+
"grad_norm": 2.5705180168151855,
|
| 316 |
+
"learning_rate": 9.90631808278867e-07,
|
| 317 |
+
"loss": 4.535789489746094,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.09803921568627451,
|
| 322 |
+
"grad_norm": 2.547631025314331,
|
| 323 |
+
"learning_rate": 9.904139433551198e-07,
|
| 324 |
+
"loss": 4.4937214851379395,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.10021786492374728,
|
| 329 |
+
"grad_norm": 2.2629098892211914,
|
| 330 |
+
"learning_rate": 9.901960784313725e-07,
|
| 331 |
+
"loss": 4.597417831420898,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.10239651416122005,
|
| 336 |
+
"grad_norm": 2.8135907649993896,
|
| 337 |
+
"learning_rate": 9.899782135076253e-07,
|
| 338 |
+
"loss": 4.574379920959473,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.10457516339869281,
|
| 343 |
+
"grad_norm": 3.0317435264587402,
|
| 344 |
+
"learning_rate": 9.89760348583878e-07,
|
| 345 |
+
"loss": 4.711512088775635,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.10675381263616558,
|
| 350 |
+
"grad_norm": 2.2007057666778564,
|
| 351 |
+
"learning_rate": 9.895424836601307e-07,
|
| 352 |
+
"loss": 4.393397331237793,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.10893246187363835,
|
| 357 |
+
"grad_norm": 1.6631900072097778,
|
| 358 |
+
"learning_rate": 9.893246187363835e-07,
|
| 359 |
+
"loss": 4.303951263427734,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.1111111111111111,
|
| 364 |
+
"grad_norm": 2.300197124481201,
|
| 365 |
+
"learning_rate": 9.89106753812636e-07,
|
| 366 |
+
"loss": 4.423295497894287,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.11328976034858387,
|
| 371 |
+
"grad_norm": 3.31419038772583,
|
| 372 |
+
"learning_rate": 9.88888888888889e-07,
|
| 373 |
+
"loss": 4.845146179199219,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.11546840958605664,
|
| 378 |
+
"grad_norm": 4.885872840881348,
|
| 379 |
+
"learning_rate": 9.886710239651415e-07,
|
| 380 |
+
"loss": 4.7251386642456055,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.11764705882352941,
|
| 385 |
+
"grad_norm": 2.013712167739868,
|
| 386 |
+
"learning_rate": 9.884531590413942e-07,
|
| 387 |
+
"loss": 4.463345527648926,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.11982570806100218,
|
| 392 |
+
"grad_norm": 2.244058132171631,
|
| 393 |
+
"learning_rate": 9.88235294117647e-07,
|
| 394 |
+
"loss": 4.357031345367432,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.12200435729847495,
|
| 399 |
+
"grad_norm": 1.6353936195373535,
|
| 400 |
+
"learning_rate": 9.880174291938997e-07,
|
| 401 |
+
"loss": 4.378466606140137,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.12418300653594772,
|
| 406 |
+
"grad_norm": 2.651231288909912,
|
| 407 |
+
"learning_rate": 9.877995642701525e-07,
|
| 408 |
+
"loss": 4.720828056335449,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.12636165577342048,
|
| 413 |
+
"grad_norm": 2.1700127124786377,
|
| 414 |
+
"learning_rate": 9.875816993464052e-07,
|
| 415 |
+
"loss": 4.482420921325684,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.12854030501089325,
|
| 420 |
+
"grad_norm": 2.560936689376831,
|
| 421 |
+
"learning_rate": 9.87363834422658e-07,
|
| 422 |
+
"loss": 4.585104942321777,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.13071895424836602,
|
| 427 |
+
"grad_norm": 1.7797707319259644,
|
| 428 |
+
"learning_rate": 9.871459694989107e-07,
|
| 429 |
+
"loss": 4.3326640129089355,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.1328976034858388,
|
| 434 |
+
"grad_norm": 2.122281312942505,
|
| 435 |
+
"learning_rate": 9.869281045751634e-07,
|
| 436 |
+
"loss": 4.474560737609863,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.13507625272331156,
|
| 441 |
+
"grad_norm": 2.31705904006958,
|
| 442 |
+
"learning_rate": 9.867102396514162e-07,
|
| 443 |
+
"loss": 4.515090465545654,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.13725490196078433,
|
| 448 |
+
"grad_norm": 1.9046130180358887,
|
| 449 |
+
"learning_rate": 9.864923747276687e-07,
|
| 450 |
+
"loss": 4.418384075164795,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.1394335511982571,
|
| 455 |
+
"grad_norm": 2.2110002040863037,
|
| 456 |
+
"learning_rate": 9.862745098039217e-07,
|
| 457 |
+
"loss": 4.565557479858398,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.14161220043572983,
|
| 462 |
+
"grad_norm": 2.6025781631469727,
|
| 463 |
+
"learning_rate": 9.860566448801742e-07,
|
| 464 |
+
"loss": 4.6747918128967285,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.1437908496732026,
|
| 469 |
+
"grad_norm": 2.562697172164917,
|
| 470 |
+
"learning_rate": 9.85838779956427e-07,
|
| 471 |
+
"loss": 4.7553181648254395,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.14596949891067537,
|
| 476 |
+
"grad_norm": 1.8945618867874146,
|
| 477 |
+
"learning_rate": 9.856209150326797e-07,
|
| 478 |
+
"loss": 4.398238658905029,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.14814814814814814,
|
| 483 |
+
"grad_norm": 2.071842670440674,
|
| 484 |
+
"learning_rate": 9.854030501089324e-07,
|
| 485 |
+
"loss": 4.499670028686523,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.1503267973856209,
|
| 490 |
+
"grad_norm": 2.426379919052124,
|
| 491 |
+
"learning_rate": 9.851851851851852e-07,
|
| 492 |
+
"loss": 4.735289573669434,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.15250544662309368,
|
| 497 |
+
"grad_norm": 2.2096705436706543,
|
| 498 |
+
"learning_rate": 9.84967320261438e-07,
|
| 499 |
+
"loss": 4.6081366539001465,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.15468409586056645,
|
| 504 |
+
"grad_norm": 2.9545485973358154,
|
| 505 |
+
"learning_rate": 9.847494553376907e-07,
|
| 506 |
+
"loss": 4.699771404266357,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.1568627450980392,
|
| 511 |
+
"grad_norm": 1.859724998474121,
|
| 512 |
+
"learning_rate": 9.845315904139432e-07,
|
| 513 |
+
"loss": 4.393412113189697,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.15904139433551198,
|
| 518 |
+
"grad_norm": 2.594811201095581,
|
| 519 |
+
"learning_rate": 9.84313725490196e-07,
|
| 520 |
+
"loss": 4.750296115875244,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.16122004357298475,
|
| 525 |
+
"grad_norm": 2.0538148880004883,
|
| 526 |
+
"learning_rate": 9.840958605664487e-07,
|
| 527 |
+
"loss": 4.523125171661377,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.16339869281045752,
|
| 532 |
+
"grad_norm": 2.1957290172576904,
|
| 533 |
+
"learning_rate": 9.838779956427014e-07,
|
| 534 |
+
"loss": 4.5541887283325195,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.1655773420479303,
|
| 539 |
+
"grad_norm": 2.0892882347106934,
|
| 540 |
+
"learning_rate": 9.836601307189542e-07,
|
| 541 |
+
"loss": 4.504140853881836,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.16775599128540306,
|
| 546 |
+
"grad_norm": 2.101895570755005,
|
| 547 |
+
"learning_rate": 9.83442265795207e-07,
|
| 548 |
+
"loss": 4.47087287902832,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.16993464052287582,
|
| 553 |
+
"grad_norm": 3.0677924156188965,
|
| 554 |
+
"learning_rate": 9.832244008714596e-07,
|
| 555 |
+
"loss": 4.681562423706055,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.1721132897603486,
|
| 560 |
+
"grad_norm": 1.7497062683105469,
|
| 561 |
+
"learning_rate": 9.830065359477124e-07,
|
| 562 |
+
"loss": 4.426023006439209,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.17429193899782136,
|
| 567 |
+
"grad_norm": 2.7591934204101562,
|
| 568 |
+
"learning_rate": 9.827886710239651e-07,
|
| 569 |
+
"loss": 4.677259922027588,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.17647058823529413,
|
| 574 |
+
"grad_norm": 1.8994778394699097,
|
| 575 |
+
"learning_rate": 9.825708061002179e-07,
|
| 576 |
+
"loss": 4.306804656982422,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.1786492374727669,
|
| 581 |
+
"grad_norm": 1.7388572692871094,
|
| 582 |
+
"learning_rate": 9.823529411764704e-07,
|
| 583 |
+
"loss": 4.367487907409668,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.18082788671023964,
|
| 588 |
+
"grad_norm": 1.8251928091049194,
|
| 589 |
+
"learning_rate": 9.821350762527234e-07,
|
| 590 |
+
"loss": 4.492748737335205,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.1830065359477124,
|
| 595 |
+
"grad_norm": 2.0507001876831055,
|
| 596 |
+
"learning_rate": 9.819172113289759e-07,
|
| 597 |
+
"loss": 4.469226360321045,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.18518518518518517,
|
| 602 |
+
"grad_norm": 3.837737798690796,
|
| 603 |
+
"learning_rate": 9.816993464052286e-07,
|
| 604 |
+
"loss": 4.880284786224365,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.18736383442265794,
|
| 609 |
+
"grad_norm": 2.32017183303833,
|
| 610 |
+
"learning_rate": 9.814814814814814e-07,
|
| 611 |
+
"loss": 4.6307244300842285,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.1895424836601307,
|
| 616 |
+
"grad_norm": 2.070546865463257,
|
| 617 |
+
"learning_rate": 9.812636165577341e-07,
|
| 618 |
+
"loss": 4.403173446655273,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.19172113289760348,
|
| 623 |
+
"grad_norm": 1.9438649415969849,
|
| 624 |
+
"learning_rate": 9.810457516339869e-07,
|
| 625 |
+
"loss": 4.322348117828369,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.19389978213507625,
|
| 630 |
+
"grad_norm": 2.0908868312835693,
|
| 631 |
+
"learning_rate": 9.808278867102396e-07,
|
| 632 |
+
"loss": 4.387789726257324,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.19607843137254902,
|
| 637 |
+
"grad_norm": 1.9938021898269653,
|
| 638 |
+
"learning_rate": 9.806100217864923e-07,
|
| 639 |
+
"loss": 4.4689040184021,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.19825708061002179,
|
| 644 |
+
"grad_norm": 2.0833871364593506,
|
| 645 |
+
"learning_rate": 9.80392156862745e-07,
|
| 646 |
+
"loss": 4.506947040557861,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.20043572984749455,
|
| 651 |
+
"grad_norm": 1.6076719760894775,
|
| 652 |
+
"learning_rate": 9.801742919389978e-07,
|
| 653 |
+
"loss": 4.388120174407959,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.20261437908496732,
|
| 658 |
+
"grad_norm": 2.3387317657470703,
|
| 659 |
+
"learning_rate": 9.799564270152506e-07,
|
| 660 |
+
"loss": 4.3787841796875,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.2047930283224401,
|
| 665 |
+
"grad_norm": 1.8435430526733398,
|
| 666 |
+
"learning_rate": 9.79738562091503e-07,
|
| 667 |
+
"loss": 4.4166035652160645,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.20697167755991286,
|
| 672 |
+
"grad_norm": 1.8981658220291138,
|
| 673 |
+
"learning_rate": 9.79520697167756e-07,
|
| 674 |
+
"loss": 4.423433303833008,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.20915032679738563,
|
| 679 |
+
"grad_norm": 2.6306850910186768,
|
| 680 |
+
"learning_rate": 9.793028322440086e-07,
|
| 681 |
+
"loss": 4.500404357910156,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.2113289760348584,
|
| 686 |
+
"grad_norm": 1.6204158067703247,
|
| 687 |
+
"learning_rate": 9.790849673202613e-07,
|
| 688 |
+
"loss": 4.223199367523193,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.21350762527233116,
|
| 693 |
+
"grad_norm": 1.995589017868042,
|
| 694 |
+
"learning_rate": 9.78867102396514e-07,
|
| 695 |
+
"loss": 4.439243793487549,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.21568627450980393,
|
| 700 |
+
"grad_norm": 2.1368906497955322,
|
| 701 |
+
"learning_rate": 9.786492374727668e-07,
|
| 702 |
+
"loss": 4.440408229827881,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.2178649237472767,
|
| 707 |
+
"grad_norm": 1.9011905193328857,
|
| 708 |
+
"learning_rate": 9.784313725490196e-07,
|
| 709 |
+
"loss": 4.256593704223633,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.22004357298474944,
|
| 714 |
+
"grad_norm": 2.1839473247528076,
|
| 715 |
+
"learning_rate": 9.782135076252723e-07,
|
| 716 |
+
"loss": 4.516264915466309,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.2222222222222222,
|
| 721 |
+
"grad_norm": 2.4889614582061768,
|
| 722 |
+
"learning_rate": 9.77995642701525e-07,
|
| 723 |
+
"loss": 4.4012908935546875,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.22440087145969498,
|
| 728 |
+
"grad_norm": 2.1062400341033936,
|
| 729 |
+
"learning_rate": 9.777777777777778e-07,
|
| 730 |
+
"loss": 4.377523899078369,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.22657952069716775,
|
| 735 |
+
"grad_norm": 2.010125160217285,
|
| 736 |
+
"learning_rate": 9.775599128540305e-07,
|
| 737 |
+
"loss": 4.375840187072754,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.22875816993464052,
|
| 742 |
+
"grad_norm": 2.392651319503784,
|
| 743 |
+
"learning_rate": 9.773420479302833e-07,
|
| 744 |
+
"loss": 4.444744110107422,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.23093681917211328,
|
| 749 |
+
"grad_norm": 1.9789717197418213,
|
| 750 |
+
"learning_rate": 9.771241830065358e-07,
|
| 751 |
+
"loss": 4.410606384277344,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.23311546840958605,
|
| 756 |
+
"grad_norm": 1.8157169818878174,
|
| 757 |
+
"learning_rate": 9.769063180827888e-07,
|
| 758 |
+
"loss": 4.317819595336914,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.23529411764705882,
|
| 763 |
+
"grad_norm": 2.4926273822784424,
|
| 764 |
+
"learning_rate": 9.766884531590413e-07,
|
| 765 |
+
"loss": 4.318043231964111,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.2374727668845316,
|
| 770 |
+
"grad_norm": 1.8115081787109375,
|
| 771 |
+
"learning_rate": 9.76470588235294e-07,
|
| 772 |
+
"loss": 4.343961238861084,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.23965141612200436,
|
| 777 |
+
"grad_norm": 2.1982710361480713,
|
| 778 |
+
"learning_rate": 9.762527233115468e-07,
|
| 779 |
+
"loss": 4.384943962097168,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.24183006535947713,
|
| 784 |
+
"grad_norm": 1.9262521266937256,
|
| 785 |
+
"learning_rate": 9.760348583877995e-07,
|
| 786 |
+
"loss": 4.344392776489258,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.2440087145969499,
|
| 791 |
+
"grad_norm": 2.537219285964966,
|
| 792 |
+
"learning_rate": 9.758169934640523e-07,
|
| 793 |
+
"loss": 4.52830171585083,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.24618736383442266,
|
| 798 |
+
"grad_norm": 2.884486675262451,
|
| 799 |
+
"learning_rate": 9.75599128540305e-07,
|
| 800 |
+
"loss": 4.582674980163574,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.24836601307189543,
|
| 805 |
+
"grad_norm": 2.7616825103759766,
|
| 806 |
+
"learning_rate": 9.753812636165577e-07,
|
| 807 |
+
"loss": 4.294858455657959,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.25054466230936817,
|
| 812 |
+
"grad_norm": 1.4845702648162842,
|
| 813 |
+
"learning_rate": 9.751633986928105e-07,
|
| 814 |
+
"loss": 4.354666233062744,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.25272331154684097,
|
| 819 |
+
"grad_norm": 1.797873854637146,
|
| 820 |
+
"learning_rate": 9.749455337690632e-07,
|
| 821 |
+
"loss": 4.310470104217529,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.2549019607843137,
|
| 826 |
+
"grad_norm": 2.25718355178833,
|
| 827 |
+
"learning_rate": 9.74727668845316e-07,
|
| 828 |
+
"loss": 4.4831223487854,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.2570806100217865,
|
| 833 |
+
"grad_norm": 2.2784883975982666,
|
| 834 |
+
"learning_rate": 9.745098039215685e-07,
|
| 835 |
+
"loss": 4.50039005279541,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.25925925925925924,
|
| 840 |
+
"grad_norm": 1.6839503049850464,
|
| 841 |
+
"learning_rate": 9.742919389978214e-07,
|
| 842 |
+
"loss": 4.3794145584106445,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.26143790849673204,
|
| 847 |
+
"grad_norm": 1.8006739616394043,
|
| 848 |
+
"learning_rate": 9.74074074074074e-07,
|
| 849 |
+
"loss": 4.287017822265625,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.2636165577342048,
|
| 854 |
+
"grad_norm": 2.229154586791992,
|
| 855 |
+
"learning_rate": 9.738562091503267e-07,
|
| 856 |
+
"loss": 4.192268371582031,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.2657952069716776,
|
| 861 |
+
"grad_norm": 2.1306228637695312,
|
| 862 |
+
"learning_rate": 9.736383442265795e-07,
|
| 863 |
+
"loss": 4.369370460510254,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.2679738562091503,
|
| 868 |
+
"grad_norm": 2.991955518722534,
|
| 869 |
+
"learning_rate": 9.734204793028322e-07,
|
| 870 |
+
"loss": 4.580495834350586,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.2701525054466231,
|
| 875 |
+
"grad_norm": 2.7565677165985107,
|
| 876 |
+
"learning_rate": 9.73202614379085e-07,
|
| 877 |
+
"loss": 4.399185657501221,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.27233115468409586,
|
| 882 |
+
"grad_norm": 2.9067633152008057,
|
| 883 |
+
"learning_rate": 9.729847494553377e-07,
|
| 884 |
+
"loss": 4.397314548492432,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.27450980392156865,
|
| 889 |
+
"grad_norm": 2.146064043045044,
|
| 890 |
+
"learning_rate": 9.727668845315904e-07,
|
| 891 |
+
"loss": 4.473128318786621,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.2766884531590414,
|
| 896 |
+
"grad_norm": 3.156425952911377,
|
| 897 |
+
"learning_rate": 9.725490196078432e-07,
|
| 898 |
+
"loss": 4.540253639221191,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.2788671023965142,
|
| 903 |
+
"grad_norm": 2.0272207260131836,
|
| 904 |
+
"learning_rate": 9.723311546840957e-07,
|
| 905 |
+
"loss": 4.391735553741455,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.28104575163398693,
|
| 910 |
+
"grad_norm": 2.0880813598632812,
|
| 911 |
+
"learning_rate": 9.721132897603487e-07,
|
| 912 |
+
"loss": 4.582479476928711,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.28322440087145967,
|
| 917 |
+
"grad_norm": 2.07149076461792,
|
| 918 |
+
"learning_rate": 9.718954248366012e-07,
|
| 919 |
+
"loss": 4.342536449432373,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.28540305010893247,
|
| 924 |
+
"grad_norm": 2.4895875453948975,
|
| 925 |
+
"learning_rate": 9.71677559912854e-07,
|
| 926 |
+
"loss": 4.407384395599365,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.2875816993464052,
|
| 931 |
+
"grad_norm": 1.7429146766662598,
|
| 932 |
+
"learning_rate": 9.714596949891067e-07,
|
| 933 |
+
"loss": 4.2959675788879395,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.289760348583878,
|
| 938 |
+
"grad_norm": 2.0402631759643555,
|
| 939 |
+
"learning_rate": 9.712418300653594e-07,
|
| 940 |
+
"loss": 4.344051837921143,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.29193899782135074,
|
| 945 |
+
"grad_norm": 2.063497304916382,
|
| 946 |
+
"learning_rate": 9.710239651416122e-07,
|
| 947 |
+
"loss": 4.3666534423828125,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.29411764705882354,
|
| 952 |
+
"grad_norm": 2.166395425796509,
|
| 953 |
+
"learning_rate": 9.70806100217865e-07,
|
| 954 |
+
"loss": 4.453709125518799,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.2962962962962963,
|
| 959 |
+
"grad_norm": 2.547016143798828,
|
| 960 |
+
"learning_rate": 9.705882352941176e-07,
|
| 961 |
+
"loss": 4.574546813964844,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.2984749455337691,
|
| 966 |
+
"grad_norm": 2.0315990447998047,
|
| 967 |
+
"learning_rate": 9.703703703703704e-07,
|
| 968 |
+
"loss": 4.206840515136719,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.3006535947712418,
|
| 973 |
+
"grad_norm": 2.6766695976257324,
|
| 974 |
+
"learning_rate": 9.701525054466231e-07,
|
| 975 |
+
"loss": 4.50142240524292,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.3028322440087146,
|
| 980 |
+
"grad_norm": 1.7705003023147583,
|
| 981 |
+
"learning_rate": 9.699346405228759e-07,
|
| 982 |
+
"loss": 4.3514580726623535,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.30501089324618735,
|
| 987 |
+
"grad_norm": 2.578533411026001,
|
| 988 |
+
"learning_rate": 9.697167755991284e-07,
|
| 989 |
+
"loss": 4.358044147491455,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.30718954248366015,
|
| 994 |
+
"grad_norm": 1.894898772239685,
|
| 995 |
+
"learning_rate": 9.694989106753814e-07,
|
| 996 |
+
"loss": 4.336588382720947,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.3093681917211329,
|
| 1001 |
+
"grad_norm": 2.2183732986450195,
|
| 1002 |
+
"learning_rate": 9.692810457516339e-07,
|
| 1003 |
+
"loss": 4.514852523803711,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.3115468409586057,
|
| 1008 |
+
"grad_norm": 3.2815968990325928,
|
| 1009 |
+
"learning_rate": 9.690631808278866e-07,
|
| 1010 |
+
"loss": 4.497104644775391,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.3137254901960784,
|
| 1015 |
+
"grad_norm": 2.4144210815429688,
|
| 1016 |
+
"learning_rate": 9.688453159041394e-07,
|
| 1017 |
+
"loss": 4.424169540405273,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.3159041394335512,
|
| 1022 |
+
"grad_norm": 2.2354543209075928,
|
| 1023 |
+
"learning_rate": 9.686274509803921e-07,
|
| 1024 |
+
"loss": 4.575407981872559,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.31808278867102396,
|
| 1029 |
+
"grad_norm": 1.9561657905578613,
|
| 1030 |
+
"learning_rate": 9.684095860566449e-07,
|
| 1031 |
+
"loss": 4.317360877990723,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.3202614379084967,
|
| 1036 |
+
"grad_norm": 2.022301435470581,
|
| 1037 |
+
"learning_rate": 9.681917211328976e-07,
|
| 1038 |
+
"loss": 4.194309234619141,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.3224400871459695,
|
| 1043 |
+
"grad_norm": 2.0781233310699463,
|
| 1044 |
+
"learning_rate": 9.679738562091503e-07,
|
| 1045 |
+
"loss": 4.375706195831299,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.32461873638344224,
|
| 1050 |
+
"grad_norm": 2.190183639526367,
|
| 1051 |
+
"learning_rate": 9.677559912854029e-07,
|
| 1052 |
+
"loss": 4.407813549041748,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.32679738562091504,
|
| 1057 |
+
"grad_norm": 2.3785204887390137,
|
| 1058 |
+
"learning_rate": 9.675381263616558e-07,
|
| 1059 |
+
"loss": 4.511362075805664,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.3289760348583878,
|
| 1064 |
+
"grad_norm": 1.4752343893051147,
|
| 1065 |
+
"learning_rate": 9.673202614379084e-07,
|
| 1066 |
+
"loss": 4.210807800292969,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.3311546840958606,
|
| 1071 |
+
"grad_norm": 2.164095401763916,
|
| 1072 |
+
"learning_rate": 9.67102396514161e-07,
|
| 1073 |
+
"loss": 4.268368244171143,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.3333333333333333,
|
| 1078 |
+
"grad_norm": 2.8139126300811768,
|
| 1079 |
+
"learning_rate": 9.668845315904138e-07,
|
| 1080 |
+
"loss": 4.446538925170898,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.3355119825708061,
|
| 1085 |
+
"grad_norm": 2.291938543319702,
|
| 1086 |
+
"learning_rate": 9.666666666666666e-07,
|
| 1087 |
+
"loss": 4.46967077255249,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.33769063180827885,
|
| 1092 |
+
"grad_norm": 1.9000574350357056,
|
| 1093 |
+
"learning_rate": 9.664488017429193e-07,
|
| 1094 |
+
"loss": 4.3823442459106445,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.33986928104575165,
|
| 1099 |
+
"grad_norm": 2.3056159019470215,
|
| 1100 |
+
"learning_rate": 9.66230936819172e-07,
|
| 1101 |
+
"loss": 4.384174823760986,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.3420479302832244,
|
| 1106 |
+
"grad_norm": 1.7677370309829712,
|
| 1107 |
+
"learning_rate": 9.660130718954248e-07,
|
| 1108 |
+
"loss": 4.266576766967773,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.3442265795206972,
|
| 1113 |
+
"grad_norm": 2.136509895324707,
|
| 1114 |
+
"learning_rate": 9.657952069716776e-07,
|
| 1115 |
+
"loss": 4.410580158233643,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.3464052287581699,
|
| 1120 |
+
"grad_norm": 2.492251396179199,
|
| 1121 |
+
"learning_rate": 9.655773420479303e-07,
|
| 1122 |
+
"loss": 4.469940662384033,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.3485838779956427,
|
| 1127 |
+
"grad_norm": 2.383185386657715,
|
| 1128 |
+
"learning_rate": 9.65359477124183e-07,
|
| 1129 |
+
"loss": 4.482204437255859,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.35076252723311546,
|
| 1134 |
+
"grad_norm": 2.1385204792022705,
|
| 1135 |
+
"learning_rate": 9.651416122004356e-07,
|
| 1136 |
+
"loss": 4.388243675231934,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.35294117647058826,
|
| 1141 |
+
"grad_norm": 2.415370464324951,
|
| 1142 |
+
"learning_rate": 9.649237472766885e-07,
|
| 1143 |
+
"loss": 4.40315055847168,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.355119825708061,
|
| 1148 |
+
"grad_norm": 2.164105176925659,
|
| 1149 |
+
"learning_rate": 9.64705882352941e-07,
|
| 1150 |
+
"loss": 4.432247161865234,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.3572984749455338,
|
| 1155 |
+
"grad_norm": 2.2456839084625244,
|
| 1156 |
+
"learning_rate": 9.644880174291938e-07,
|
| 1157 |
+
"loss": 4.266363143920898,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.35947712418300654,
|
| 1162 |
+
"grad_norm": 2.361248016357422,
|
| 1163 |
+
"learning_rate": 9.642701525054465e-07,
|
| 1164 |
+
"loss": 4.5409650802612305,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.3616557734204793,
|
| 1169 |
+
"grad_norm": 3.0007307529449463,
|
| 1170 |
+
"learning_rate": 9.640522875816993e-07,
|
| 1171 |
+
"loss": 4.580550670623779,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.3638344226579521,
|
| 1176 |
+
"grad_norm": 1.6576095819473267,
|
| 1177 |
+
"learning_rate": 9.63834422657952e-07,
|
| 1178 |
+
"loss": 4.340091228485107,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.3660130718954248,
|
| 1183 |
+
"grad_norm": 1.9235918521881104,
|
| 1184 |
+
"learning_rate": 9.636165577342048e-07,
|
| 1185 |
+
"loss": 4.221652030944824,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.3681917211328976,
|
| 1190 |
+
"grad_norm": 2.0118086338043213,
|
| 1191 |
+
"learning_rate": 9.633986928104575e-07,
|
| 1192 |
+
"loss": 4.3488874435424805,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.37037037037037035,
|
| 1197 |
+
"grad_norm": 2.1841843128204346,
|
| 1198 |
+
"learning_rate": 9.631808278867103e-07,
|
| 1199 |
+
"loss": 4.367924213409424,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.37254901960784315,
|
| 1204 |
+
"grad_norm": 2.247666835784912,
|
| 1205 |
+
"learning_rate": 9.629629629629628e-07,
|
| 1206 |
+
"loss": 4.505679607391357,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.3747276688453159,
|
| 1211 |
+
"grad_norm": 1.8381444215774536,
|
| 1212 |
+
"learning_rate": 9.627450980392157e-07,
|
| 1213 |
+
"loss": 4.235549449920654,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.3769063180827887,
|
| 1218 |
+
"grad_norm": 2.7297332286834717,
|
| 1219 |
+
"learning_rate": 9.625272331154683e-07,
|
| 1220 |
+
"loss": 4.471020221710205,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.3790849673202614,
|
| 1225 |
+
"grad_norm": 1.9857988357543945,
|
| 1226 |
+
"learning_rate": 9.62309368191721e-07,
|
| 1227 |
+
"loss": 4.335488319396973,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.3812636165577342,
|
| 1232 |
+
"grad_norm": 1.8306801319122314,
|
| 1233 |
+
"learning_rate": 9.620915032679738e-07,
|
| 1234 |
+
"loss": 4.086997985839844,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.38344226579520696,
|
| 1239 |
+
"grad_norm": 1.687875747680664,
|
| 1240 |
+
"learning_rate": 9.618736383442265e-07,
|
| 1241 |
+
"loss": 4.265539169311523,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.38562091503267976,
|
| 1246 |
+
"grad_norm": 1.860582947731018,
|
| 1247 |
+
"learning_rate": 9.616557734204792e-07,
|
| 1248 |
+
"loss": 4.2574849128723145,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.3877995642701525,
|
| 1253 |
+
"grad_norm": 2.502021312713623,
|
| 1254 |
+
"learning_rate": 9.61437908496732e-07,
|
| 1255 |
+
"loss": 4.495733737945557,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.3899782135076253,
|
| 1260 |
+
"grad_norm": 1.581700325012207,
|
| 1261 |
+
"learning_rate": 9.612200435729847e-07,
|
| 1262 |
+
"loss": 4.240194320678711,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.39215686274509803,
|
| 1267 |
+
"grad_norm": 2.7113497257232666,
|
| 1268 |
+
"learning_rate": 9.610021786492375e-07,
|
| 1269 |
+
"loss": 4.6046671867370605,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.39433551198257083,
|
| 1274 |
+
"grad_norm": 2.4433610439300537,
|
| 1275 |
+
"learning_rate": 9.607843137254902e-07,
|
| 1276 |
+
"loss": 4.441323280334473,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.39651416122004357,
|
| 1281 |
+
"grad_norm": 1.9853641986846924,
|
| 1282 |
+
"learning_rate": 9.60566448801743e-07,
|
| 1283 |
+
"loss": 4.359451770782471,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.39869281045751637,
|
| 1288 |
+
"grad_norm": 2.133108377456665,
|
| 1289 |
+
"learning_rate": 9.603485838779955e-07,
|
| 1290 |
+
"loss": 4.289493083953857,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.4008714596949891,
|
| 1295 |
+
"grad_norm": 1.7538727521896362,
|
| 1296 |
+
"learning_rate": 9.601307189542484e-07,
|
| 1297 |
+
"loss": 4.28318452835083,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.40305010893246185,
|
| 1302 |
+
"grad_norm": 3.3512535095214844,
|
| 1303 |
+
"learning_rate": 9.59912854030501e-07,
|
| 1304 |
+
"loss": 4.550060272216797,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.40522875816993464,
|
| 1309 |
+
"grad_norm": 1.5646427869796753,
|
| 1310 |
+
"learning_rate": 9.596949891067537e-07,
|
| 1311 |
+
"loss": 4.34261417388916,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.4074074074074074,
|
| 1316 |
+
"grad_norm": 1.7791746854782104,
|
| 1317 |
+
"learning_rate": 9.594771241830065e-07,
|
| 1318 |
+
"loss": 4.240348815917969,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.4095860566448802,
|
| 1323 |
+
"grad_norm": 2.326260805130005,
|
| 1324 |
+
"learning_rate": 9.592592592592592e-07,
|
| 1325 |
+
"loss": 4.4669952392578125,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.4117647058823529,
|
| 1330 |
+
"grad_norm": 1.837967038154602,
|
| 1331 |
+
"learning_rate": 9.59041394335512e-07,
|
| 1332 |
+
"loss": 4.39886474609375,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.4139433551198257,
|
| 1337 |
+
"grad_norm": 1.744829535484314,
|
| 1338 |
+
"learning_rate": 9.588235294117647e-07,
|
| 1339 |
+
"loss": 4.2220540046691895,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.41612200435729846,
|
| 1344 |
+
"grad_norm": 1.8719234466552734,
|
| 1345 |
+
"learning_rate": 9.586056644880174e-07,
|
| 1346 |
+
"loss": 4.2246575355529785,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.41830065359477125,
|
| 1351 |
+
"grad_norm": 2.3283026218414307,
|
| 1352 |
+
"learning_rate": 9.583877995642702e-07,
|
| 1353 |
+
"loss": 4.3507843017578125,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.420479302832244,
|
| 1358 |
+
"grad_norm": 1.8943367004394531,
|
| 1359 |
+
"learning_rate": 9.58169934640523e-07,
|
| 1360 |
+
"loss": 4.162900924682617,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.4226579520697168,
|
| 1365 |
+
"grad_norm": 2.661996364593506,
|
| 1366 |
+
"learning_rate": 9.579520697167757e-07,
|
| 1367 |
+
"loss": 4.450239658355713,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.42483660130718953,
|
| 1372 |
+
"grad_norm": 2.0999133586883545,
|
| 1373 |
+
"learning_rate": 9.577342047930282e-07,
|
| 1374 |
+
"loss": 4.250425338745117,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.42701525054466233,
|
| 1379 |
+
"grad_norm": 1.9673007726669312,
|
| 1380 |
+
"learning_rate": 9.575163398692811e-07,
|
| 1381 |
+
"loss": 4.474855422973633,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.42919389978213507,
|
| 1386 |
+
"grad_norm": 1.8445521593093872,
|
| 1387 |
+
"learning_rate": 9.572984749455337e-07,
|
| 1388 |
+
"loss": 4.2301716804504395,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.43137254901960786,
|
| 1393 |
+
"grad_norm": 2.857212781906128,
|
| 1394 |
+
"learning_rate": 9.570806100217864e-07,
|
| 1395 |
+
"loss": 4.531691551208496,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.4335511982570806,
|
| 1400 |
+
"grad_norm": 2.1888811588287354,
|
| 1401 |
+
"learning_rate": 9.568627450980392e-07,
|
| 1402 |
+
"loss": 4.4800615310668945,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.4357298474945534,
|
| 1407 |
+
"grad_norm": 1.7973730564117432,
|
| 1408 |
+
"learning_rate": 9.566448801742919e-07,
|
| 1409 |
+
"loss": 4.28166389465332,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.43790849673202614,
|
| 1414 |
+
"grad_norm": 3.003615140914917,
|
| 1415 |
+
"learning_rate": 9.564270152505446e-07,
|
| 1416 |
+
"loss": 4.628840446472168,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.4400871459694989,
|
| 1421 |
+
"grad_norm": 1.9880698919296265,
|
| 1422 |
+
"learning_rate": 9.562091503267974e-07,
|
| 1423 |
+
"loss": 4.241949558258057,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.4422657952069717,
|
| 1428 |
+
"grad_norm": 1.7790374755859375,
|
| 1429 |
+
"learning_rate": 9.559912854030501e-07,
|
| 1430 |
+
"loss": 4.304915904998779,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.4444444444444444,
|
| 1435 |
+
"grad_norm": 1.8285244703292847,
|
| 1436 |
+
"learning_rate": 9.557734204793029e-07,
|
| 1437 |
+
"loss": 4.2064104080200195,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.4466230936819172,
|
| 1442 |
+
"grad_norm": 2.522207260131836,
|
| 1443 |
+
"learning_rate": 9.555555555555556e-07,
|
| 1444 |
+
"loss": 4.3665032386779785,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.44880174291938996,
|
| 1449 |
+
"grad_norm": 2.157550573348999,
|
| 1450 |
+
"learning_rate": 9.553376906318083e-07,
|
| 1451 |
+
"loss": 4.449486255645752,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.45098039215686275,
|
| 1456 |
+
"grad_norm": 2.3344943523406982,
|
| 1457 |
+
"learning_rate": 9.551198257080609e-07,
|
| 1458 |
+
"loss": 4.397902488708496,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.4531590413943355,
|
| 1463 |
+
"grad_norm": 1.9231369495391846,
|
| 1464 |
+
"learning_rate": 9.549019607843138e-07,
|
| 1465 |
+
"loss": 4.240512847900391,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.4553376906318083,
|
| 1470 |
+
"grad_norm": 2.3051517009735107,
|
| 1471 |
+
"learning_rate": 9.546840958605664e-07,
|
| 1472 |
+
"loss": 4.396009922027588,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.45751633986928103,
|
| 1477 |
+
"grad_norm": 1.9424047470092773,
|
| 1478 |
+
"learning_rate": 9.544662309368191e-07,
|
| 1479 |
+
"loss": 4.256721019744873,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.4596949891067538,
|
| 1484 |
+
"grad_norm": 1.8167564868927002,
|
| 1485 |
+
"learning_rate": 9.542483660130718e-07,
|
| 1486 |
+
"loss": 4.232820510864258,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.46187363834422657,
|
| 1491 |
+
"grad_norm": 2.1137053966522217,
|
| 1492 |
+
"learning_rate": 9.540305010893246e-07,
|
| 1493 |
+
"loss": 4.301129341125488,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.46405228758169936,
|
| 1498 |
+
"grad_norm": 2.390566349029541,
|
| 1499 |
+
"learning_rate": 9.538126361655773e-07,
|
| 1500 |
+
"loss": 4.2755656242370605,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.4662309368191721,
|
| 1505 |
+
"grad_norm": 2.054520845413208,
|
| 1506 |
+
"learning_rate": 9.535947712418301e-07,
|
| 1507 |
+
"loss": 4.281137943267822,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.4684095860566449,
|
| 1512 |
+
"grad_norm": 1.689180612564087,
|
| 1513 |
+
"learning_rate": 9.533769063180827e-07,
|
| 1514 |
+
"loss": 4.184370040893555,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.47058823529411764,
|
| 1519 |
+
"grad_norm": 1.9673049449920654,
|
| 1520 |
+
"learning_rate": 9.531590413943355e-07,
|
| 1521 |
+
"loss": 4.297755241394043,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.47276688453159044,
|
| 1526 |
+
"grad_norm": 2.2872281074523926,
|
| 1527 |
+
"learning_rate": 9.529411764705881e-07,
|
| 1528 |
+
"loss": 4.3808817863464355,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.4749455337690632,
|
| 1533 |
+
"grad_norm": 2.2688164710998535,
|
| 1534 |
+
"learning_rate": 9.527233115468409e-07,
|
| 1535 |
+
"loss": 4.442854404449463,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.477124183006536,
|
| 1540 |
+
"grad_norm": 2.626431703567505,
|
| 1541 |
+
"learning_rate": 9.525054466230936e-07,
|
| 1542 |
+
"loss": 4.416866302490234,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.4793028322440087,
|
| 1547 |
+
"grad_norm": 2.3252599239349365,
|
| 1548 |
+
"learning_rate": 9.522875816993463e-07,
|
| 1549 |
+
"loss": 4.290740013122559,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.48148148148148145,
|
| 1554 |
+
"grad_norm": 2.6100525856018066,
|
| 1555 |
+
"learning_rate": 9.520697167755991e-07,
|
| 1556 |
+
"loss": 4.216197490692139,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.48366013071895425,
|
| 1561 |
+
"grad_norm": 2.0119993686676025,
|
| 1562 |
+
"learning_rate": 9.518518518518518e-07,
|
| 1563 |
+
"loss": 4.252105236053467,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.485838779956427,
|
| 1568 |
+
"grad_norm": 2.0626165866851807,
|
| 1569 |
+
"learning_rate": 9.516339869281044e-07,
|
| 1570 |
+
"loss": 4.326197624206543,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.4880174291938998,
|
| 1575 |
+
"grad_norm": 1.8896783590316772,
|
| 1576 |
+
"learning_rate": 9.514161220043573e-07,
|
| 1577 |
+
"loss": 4.099881649017334,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.49019607843137253,
|
| 1582 |
+
"grad_norm": 1.7077407836914062,
|
| 1583 |
+
"learning_rate": 9.511982570806099e-07,
|
| 1584 |
+
"loss": 4.1440558433532715,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.4923747276688453,
|
| 1589 |
+
"grad_norm": 1.8319593667984009,
|
| 1590 |
+
"learning_rate": 9.509803921568627e-07,
|
| 1591 |
+
"loss": 4.277885913848877,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.49455337690631807,
|
| 1596 |
+
"grad_norm": 2.157092332839966,
|
| 1597 |
+
"learning_rate": 9.507625272331154e-07,
|
| 1598 |
+
"loss": 4.496051788330078,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.49673202614379086,
|
| 1603 |
+
"grad_norm": 1.6478551626205444,
|
| 1604 |
+
"learning_rate": 9.505446623093682e-07,
|
| 1605 |
+
"loss": 4.266190528869629,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.4989106753812636,
|
| 1610 |
+
"grad_norm": 1.7191162109375,
|
| 1611 |
+
"learning_rate": 9.503267973856208e-07,
|
| 1612 |
+
"loss": 4.236968994140625,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.5010893246187363,
|
| 1617 |
+
"grad_norm": 1.7083362340927124,
|
| 1618 |
+
"learning_rate": 9.501089324618736e-07,
|
| 1619 |
+
"loss": 4.369157791137695,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.5032679738562091,
|
| 1624 |
+
"grad_norm": 2.716724157333374,
|
| 1625 |
+
"learning_rate": 9.498910675381263e-07,
|
| 1626 |
+
"loss": 4.3496317863464355,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.5054466230936819,
|
| 1631 |
+
"grad_norm": 1.9012598991394043,
|
| 1632 |
+
"learning_rate": 9.49673202614379e-07,
|
| 1633 |
+
"loss": 4.437310695648193,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.5076252723311547,
|
| 1638 |
+
"grad_norm": 2.0860955715179443,
|
| 1639 |
+
"learning_rate": 9.494553376906318e-07,
|
| 1640 |
+
"loss": 4.3534345626831055,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.5098039215686274,
|
| 1645 |
+
"grad_norm": 1.9643157720565796,
|
| 1646 |
+
"learning_rate": 9.492374727668845e-07,
|
| 1647 |
+
"loss": 4.349437236785889,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.5119825708061002,
|
| 1652 |
+
"grad_norm": 2.047245502471924,
|
| 1653 |
+
"learning_rate": 9.490196078431371e-07,
|
| 1654 |
+
"loss": 4.356471061706543,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.514161220043573,
|
| 1659 |
+
"grad_norm": 1.9418092966079712,
|
| 1660 |
+
"learning_rate": 9.4880174291939e-07,
|
| 1661 |
+
"loss": 4.271924018859863,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.5163398692810458,
|
| 1666 |
+
"grad_norm": 1.984614372253418,
|
| 1667 |
+
"learning_rate": 9.485838779956426e-07,
|
| 1668 |
+
"loss": 4.043069839477539,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.5185185185185185,
|
| 1673 |
+
"grad_norm": 2.2965073585510254,
|
| 1674 |
+
"learning_rate": 9.483660130718954e-07,
|
| 1675 |
+
"loss": 4.426994323730469,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.5206971677559913,
|
| 1680 |
+
"grad_norm": 1.6690049171447754,
|
| 1681 |
+
"learning_rate": 9.481481481481481e-07,
|
| 1682 |
+
"loss": 4.222958087921143,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.5228758169934641,
|
| 1687 |
+
"grad_norm": 2.3808162212371826,
|
| 1688 |
+
"learning_rate": 9.479302832244009e-07,
|
| 1689 |
+
"loss": 4.478995323181152,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.5250544662309368,
|
| 1694 |
+
"grad_norm": 1.7484283447265625,
|
| 1695 |
+
"learning_rate": 9.477124183006535e-07,
|
| 1696 |
+
"loss": 4.249248027801514,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.5272331154684096,
|
| 1701 |
+
"grad_norm": 2.5079264640808105,
|
| 1702 |
+
"learning_rate": 9.474945533769063e-07,
|
| 1703 |
+
"loss": 4.2816548347473145,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.5294117647058824,
|
| 1708 |
+
"grad_norm": 2.8622679710388184,
|
| 1709 |
+
"learning_rate": 9.47276688453159e-07,
|
| 1710 |
+
"loss": 4.538039207458496,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.5315904139433552,
|
| 1715 |
+
"grad_norm": 2.358126163482666,
|
| 1716 |
+
"learning_rate": 9.470588235294117e-07,
|
| 1717 |
+
"loss": 4.52814245223999,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.5337690631808278,
|
| 1722 |
+
"grad_norm": 2.1673479080200195,
|
| 1723 |
+
"learning_rate": 9.468409586056645e-07,
|
| 1724 |
+
"loss": 4.197198867797852,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.5359477124183006,
|
| 1729 |
+
"grad_norm": 2.0004494190216064,
|
| 1730 |
+
"learning_rate": 9.466230936819172e-07,
|
| 1731 |
+
"loss": 4.114048480987549,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.5381263616557734,
|
| 1736 |
+
"grad_norm": 1.7733162641525269,
|
| 1737 |
+
"learning_rate": 9.464052287581698e-07,
|
| 1738 |
+
"loss": 4.3549065589904785,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.5403050108932462,
|
| 1743 |
+
"grad_norm": 2.3709092140197754,
|
| 1744 |
+
"learning_rate": 9.461873638344227e-07,
|
| 1745 |
+
"loss": 4.270395278930664,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.5424836601307189,
|
| 1750 |
+
"grad_norm": 1.7482978105545044,
|
| 1751 |
+
"learning_rate": 9.459694989106753e-07,
|
| 1752 |
+
"loss": 4.320254325866699,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.5446623093681917,
|
| 1757 |
+
"grad_norm": 1.8241703510284424,
|
| 1758 |
+
"learning_rate": 9.457516339869281e-07,
|
| 1759 |
+
"loss": 4.232961654663086,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.5468409586056645,
|
| 1764 |
+
"grad_norm": 2.852616786956787,
|
| 1765 |
+
"learning_rate": 9.455337690631808e-07,
|
| 1766 |
+
"loss": 4.582944393157959,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.5490196078431373,
|
| 1771 |
+
"grad_norm": 2.2779054641723633,
|
| 1772 |
+
"learning_rate": 9.453159041394335e-07,
|
| 1773 |
+
"loss": 4.473123550415039,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.55119825708061,
|
| 1778 |
+
"grad_norm": 2.315554618835449,
|
| 1779 |
+
"learning_rate": 9.450980392156862e-07,
|
| 1780 |
+
"loss": 4.4862141609191895,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.5533769063180828,
|
| 1785 |
+
"grad_norm": 1.513036847114563,
|
| 1786 |
+
"learning_rate": 9.44880174291939e-07,
|
| 1787 |
+
"loss": 4.0746355056762695,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.5555555555555556,
|
| 1792 |
+
"grad_norm": 2.1710667610168457,
|
| 1793 |
+
"learning_rate": 9.446623093681917e-07,
|
| 1794 |
+
"loss": 4.378049850463867,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.5577342047930284,
|
| 1799 |
+
"grad_norm": 2.427969217300415,
|
| 1800 |
+
"learning_rate": 9.444444444444444e-07,
|
| 1801 |
+
"loss": 4.507735252380371,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.5599128540305011,
|
| 1806 |
+
"grad_norm": 2.7602696418762207,
|
| 1807 |
+
"learning_rate": 9.442265795206972e-07,
|
| 1808 |
+
"loss": 4.3347368240356445,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.5620915032679739,
|
| 1813 |
+
"grad_norm": 2.0364744663238525,
|
| 1814 |
+
"learning_rate": 9.440087145969499e-07,
|
| 1815 |
+
"loss": 4.31652307510376,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.5642701525054467,
|
| 1820 |
+
"grad_norm": 2.303499698638916,
|
| 1821 |
+
"learning_rate": 9.437908496732025e-07,
|
| 1822 |
+
"loss": 4.130202770233154,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.5664488017429193,
|
| 1827 |
+
"grad_norm": 1.4112861156463623,
|
| 1828 |
+
"learning_rate": 9.435729847494554e-07,
|
| 1829 |
+
"loss": 4.151785850524902,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.5686274509803921,
|
| 1834 |
+
"grad_norm": 1.8270570039749146,
|
| 1835 |
+
"learning_rate": 9.43355119825708e-07,
|
| 1836 |
+
"loss": 4.369143486022949,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.5708061002178649,
|
| 1841 |
+
"grad_norm": 2.8040060997009277,
|
| 1842 |
+
"learning_rate": 9.431372549019608e-07,
|
| 1843 |
+
"loss": 4.293192386627197,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.5729847494553377,
|
| 1848 |
+
"grad_norm": 2.1216909885406494,
|
| 1849 |
+
"learning_rate": 9.429193899782135e-07,
|
| 1850 |
+
"loss": 4.178761005401611,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.5751633986928104,
|
| 1855 |
+
"grad_norm": 3.012073040008545,
|
| 1856 |
+
"learning_rate": 9.427015250544662e-07,
|
| 1857 |
+
"loss": 4.526463985443115,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.5773420479302832,
|
| 1862 |
+
"grad_norm": 2.417126417160034,
|
| 1863 |
+
"learning_rate": 9.424836601307189e-07,
|
| 1864 |
+
"loss": 4.480845928192139,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.579520697167756,
|
| 1869 |
+
"grad_norm": 1.8935476541519165,
|
| 1870 |
+
"learning_rate": 9.422657952069716e-07,
|
| 1871 |
+
"loss": 4.2331318855285645,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.5816993464052288,
|
| 1876 |
+
"grad_norm": 2.131685733795166,
|
| 1877 |
+
"learning_rate": 9.420479302832244e-07,
|
| 1878 |
+
"loss": 4.164639949798584,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.5838779956427015,
|
| 1883 |
+
"grad_norm": 1.919486165046692,
|
| 1884 |
+
"learning_rate": 9.418300653594771e-07,
|
| 1885 |
+
"loss": 4.158851146697998,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.5860566448801743,
|
| 1890 |
+
"grad_norm": 1.8236701488494873,
|
| 1891 |
+
"learning_rate": 9.416122004357297e-07,
|
| 1892 |
+
"loss": 4.261025905609131,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.5882352941176471,
|
| 1897 |
+
"grad_norm": 1.9933416843414307,
|
| 1898 |
+
"learning_rate": 9.413943355119826e-07,
|
| 1899 |
+
"loss": 4.264568328857422,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.5904139433551199,
|
| 1904 |
+
"grad_norm": 2.719871759414673,
|
| 1905 |
+
"learning_rate": 9.411764705882352e-07,
|
| 1906 |
+
"loss": 4.393710613250732,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.5925925925925926,
|
| 1911 |
+
"grad_norm": 2.377943992614746,
|
| 1912 |
+
"learning_rate": 9.40958605664488e-07,
|
| 1913 |
+
"loss": 4.4187188148498535,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.5947712418300654,
|
| 1918 |
+
"grad_norm": 1.8118345737457275,
|
| 1919 |
+
"learning_rate": 9.407407407407407e-07,
|
| 1920 |
+
"loss": 4.238672733306885,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.5969498910675382,
|
| 1925 |
+
"grad_norm": 3.0528037548065186,
|
| 1926 |
+
"learning_rate": 9.405228758169935e-07,
|
| 1927 |
+
"loss": 4.501391887664795,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.599128540305011,
|
| 1932 |
+
"grad_norm": 1.970699667930603,
|
| 1933 |
+
"learning_rate": 9.403050108932461e-07,
|
| 1934 |
+
"loss": 4.277827739715576,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.6013071895424836,
|
| 1939 |
+
"grad_norm": 2.3799169063568115,
|
| 1940 |
+
"learning_rate": 9.400871459694989e-07,
|
| 1941 |
+
"loss": 4.331878662109375,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.6034858387799564,
|
| 1946 |
+
"grad_norm": 1.6306818723678589,
|
| 1947 |
+
"learning_rate": 9.398692810457516e-07,
|
| 1948 |
+
"loss": 4.269891738891602,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.6056644880174292,
|
| 1953 |
+
"grad_norm": 2.062476873397827,
|
| 1954 |
+
"learning_rate": 9.396514161220042e-07,
|
| 1955 |
+
"loss": 4.327604293823242,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.6078431372549019,
|
| 1960 |
+
"grad_norm": 2.5334386825561523,
|
| 1961 |
+
"learning_rate": 9.394335511982571e-07,
|
| 1962 |
+
"loss": 4.333818435668945,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.6100217864923747,
|
| 1967 |
+
"grad_norm": 2.0433833599090576,
|
| 1968 |
+
"learning_rate": 9.392156862745097e-07,
|
| 1969 |
+
"loss": 4.203022003173828,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.6122004357298475,
|
| 1974 |
+
"grad_norm": 2.2614269256591797,
|
| 1975 |
+
"learning_rate": 9.389978213507624e-07,
|
| 1976 |
+
"loss": 4.318673133850098,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.6143790849673203,
|
| 1981 |
+
"grad_norm": 1.9716330766677856,
|
| 1982 |
+
"learning_rate": 9.387799564270152e-07,
|
| 1983 |
+
"loss": 4.232147693634033,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.616557734204793,
|
| 1988 |
+
"grad_norm": 1.837843418121338,
|
| 1989 |
+
"learning_rate": 9.385620915032679e-07,
|
| 1990 |
+
"loss": 4.245857238769531,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.6187363834422658,
|
| 1995 |
+
"grad_norm": 2.3850011825561523,
|
| 1996 |
+
"learning_rate": 9.383442265795206e-07,
|
| 1997 |
+
"loss": 4.42717981338501,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.6209150326797386,
|
| 2002 |
+
"grad_norm": 2.4741547107696533,
|
| 2003 |
+
"learning_rate": 9.381263616557734e-07,
|
| 2004 |
+
"loss": 4.136049747467041,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.6230936819172114,
|
| 2009 |
+
"grad_norm": 1.8070532083511353,
|
| 2010 |
+
"learning_rate": 9.37908496732026e-07,
|
| 2011 |
+
"loss": 4.264199733734131,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.6252723311546841,
|
| 2016 |
+
"grad_norm": 2.5413472652435303,
|
| 2017 |
+
"learning_rate": 9.376906318082788e-07,
|
| 2018 |
+
"loss": 4.469062328338623,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.6274509803921569,
|
| 2023 |
+
"grad_norm": 1.9982818365097046,
|
| 2024 |
+
"learning_rate": 9.374727668845315e-07,
|
| 2025 |
+
"loss": 4.051740646362305,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.6296296296296297,
|
| 2030 |
+
"grad_norm": 2.351032018661499,
|
| 2031 |
+
"learning_rate": 9.372549019607843e-07,
|
| 2032 |
+
"loss": 4.301977634429932,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.6318082788671024,
|
| 2037 |
+
"grad_norm": 1.9607293605804443,
|
| 2038 |
+
"learning_rate": 9.370370370370369e-07,
|
| 2039 |
+
"loss": 4.261730194091797,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.6339869281045751,
|
| 2044 |
+
"grad_norm": 1.9776970148086548,
|
| 2045 |
+
"learning_rate": 9.368191721132898e-07,
|
| 2046 |
+
"loss": 4.373515605926514,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.6361655773420479,
|
| 2051 |
+
"grad_norm": 2.6956138610839844,
|
| 2052 |
+
"learning_rate": 9.366013071895424e-07,
|
| 2053 |
+
"loss": 4.401850700378418,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.6383442265795207,
|
| 2058 |
+
"grad_norm": 2.6304495334625244,
|
| 2059 |
+
"learning_rate": 9.363834422657951e-07,
|
| 2060 |
+
"loss": 4.5218892097473145,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.6405228758169934,
|
| 2065 |
+
"grad_norm": 2.0205626487731934,
|
| 2066 |
+
"learning_rate": 9.361655773420479e-07,
|
| 2067 |
+
"loss": 4.327292442321777,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.6427015250544662,
|
| 2072 |
+
"grad_norm": 2.179348945617676,
|
| 2073 |
+
"learning_rate": 9.359477124183006e-07,
|
| 2074 |
+
"loss": 4.2162299156188965,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.644880174291939,
|
| 2079 |
+
"grad_norm": 2.004915952682495,
|
| 2080 |
+
"learning_rate": 9.357298474945533e-07,
|
| 2081 |
+
"loss": 4.26617956161499,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.6470588235294118,
|
| 2086 |
+
"grad_norm": 2.487010955810547,
|
| 2087 |
+
"learning_rate": 9.355119825708061e-07,
|
| 2088 |
+
"loss": 4.518709182739258,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.6492374727668845,
|
| 2093 |
+
"grad_norm": 2.1379663944244385,
|
| 2094 |
+
"learning_rate": 9.352941176470588e-07,
|
| 2095 |
+
"loss": 4.301877975463867,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.6514161220043573,
|
| 2100 |
+
"grad_norm": 2.1979153156280518,
|
| 2101 |
+
"learning_rate": 9.350762527233115e-07,
|
| 2102 |
+
"loss": 4.34274959564209,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.6535947712418301,
|
| 2107 |
+
"grad_norm": 1.719846487045288,
|
| 2108 |
+
"learning_rate": 9.348583877995642e-07,
|
| 2109 |
+
"loss": 4.1293253898620605,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.6557734204793029,
|
| 2114 |
+
"grad_norm": 1.7805875539779663,
|
| 2115 |
+
"learning_rate": 9.34640522875817e-07,
|
| 2116 |
+
"loss": 4.257225513458252,
|
| 2117 |
+
"step": 301
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.6579520697167756,
|
| 2121 |
+
"grad_norm": 1.6562926769256592,
|
| 2122 |
+
"learning_rate": 9.344226579520696e-07,
|
| 2123 |
+
"loss": 4.225170135498047,
|
| 2124 |
+
"step": 302
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.6601307189542484,
|
| 2128 |
+
"grad_norm": 1.9313156604766846,
|
| 2129 |
+
"learning_rate": 9.342047930283225e-07,
|
| 2130 |
+
"loss": 4.125218868255615,
|
| 2131 |
+
"step": 303
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.6623093681917211,
|
| 2135 |
+
"grad_norm": 3.258147716522217,
|
| 2136 |
+
"learning_rate": 9.339869281045751e-07,
|
| 2137 |
+
"loss": 4.621779441833496,
|
| 2138 |
+
"step": 304
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.664488017429194,
|
| 2142 |
+
"grad_norm": 2.9603540897369385,
|
| 2143 |
+
"learning_rate": 9.337690631808278e-07,
|
| 2144 |
+
"loss": 4.509817600250244,
|
| 2145 |
+
"step": 305
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.6666666666666666,
|
| 2149 |
+
"grad_norm": 2.6384479999542236,
|
| 2150 |
+
"learning_rate": 9.335511982570806e-07,
|
| 2151 |
+
"loss": 4.355105876922607,
|
| 2152 |
+
"step": 306
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.6688453159041394,
|
| 2156 |
+
"grad_norm": 2.2285590171813965,
|
| 2157 |
+
"learning_rate": 9.333333333333333e-07,
|
| 2158 |
+
"loss": 4.502842903137207,
|
| 2159 |
+
"step": 307
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.6710239651416122,
|
| 2163 |
+
"grad_norm": 2.0646419525146484,
|
| 2164 |
+
"learning_rate": 9.33115468409586e-07,
|
| 2165 |
+
"loss": 4.261293888092041,
|
| 2166 |
+
"step": 308
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.673202614379085,
|
| 2170 |
+
"grad_norm": 2.292961359024048,
|
| 2171 |
+
"learning_rate": 9.328976034858388e-07,
|
| 2172 |
+
"loss": 4.331558704376221,
|
| 2173 |
+
"step": 309
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.6753812636165577,
|
| 2177 |
+
"grad_norm": 3.0116658210754395,
|
| 2178 |
+
"learning_rate": 9.326797385620914e-07,
|
| 2179 |
+
"loss": 4.40883731842041,
|
| 2180 |
+
"step": 310
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.6775599128540305,
|
| 2184 |
+
"grad_norm": 2.169278144836426,
|
| 2185 |
+
"learning_rate": 9.324618736383442e-07,
|
| 2186 |
+
"loss": 4.30955696105957,
|
| 2187 |
+
"step": 311
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.6797385620915033,
|
| 2191 |
+
"grad_norm": 2.6467745304107666,
|
| 2192 |
+
"learning_rate": 9.322440087145968e-07,
|
| 2193 |
+
"loss": 4.36649751663208,
|
| 2194 |
+
"step": 312
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.681917211328976,
|
| 2198 |
+
"grad_norm": 2.6238508224487305,
|
| 2199 |
+
"learning_rate": 9.320261437908497e-07,
|
| 2200 |
+
"loss": 4.338852882385254,
|
| 2201 |
+
"step": 313
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.6840958605664488,
|
| 2205 |
+
"grad_norm": 2.0027642250061035,
|
| 2206 |
+
"learning_rate": 9.318082788671023e-07,
|
| 2207 |
+
"loss": 4.211042881011963,
|
| 2208 |
+
"step": 314
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.6862745098039216,
|
| 2212 |
+
"grad_norm": 1.822209358215332,
|
| 2213 |
+
"learning_rate": 9.315904139433551e-07,
|
| 2214 |
+
"loss": 4.39182186126709,
|
| 2215 |
+
"step": 315
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.6884531590413944,
|
| 2219 |
+
"grad_norm": 2.1167984008789062,
|
| 2220 |
+
"learning_rate": 9.313725490196078e-07,
|
| 2221 |
+
"loss": 4.396923065185547,
|
| 2222 |
+
"step": 316
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.690631808278867,
|
| 2226 |
+
"grad_norm": 1.6318403482437134,
|
| 2227 |
+
"learning_rate": 9.311546840958605e-07,
|
| 2228 |
+
"loss": 4.246094226837158,
|
| 2229 |
+
"step": 317
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.6928104575163399,
|
| 2233 |
+
"grad_norm": 1.8685541152954102,
|
| 2234 |
+
"learning_rate": 9.309368191721132e-07,
|
| 2235 |
+
"loss": 4.165795803070068,
|
| 2236 |
+
"step": 318
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.6949891067538126,
|
| 2240 |
+
"grad_norm": 1.9460184574127197,
|
| 2241 |
+
"learning_rate": 9.30718954248366e-07,
|
| 2242 |
+
"loss": 4.289465427398682,
|
| 2243 |
+
"step": 319
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.6971677559912854,
|
| 2247 |
+
"grad_norm": 2.909140110015869,
|
| 2248 |
+
"learning_rate": 9.305010893246187e-07,
|
| 2249 |
+
"loss": 4.520230293273926,
|
| 2250 |
+
"step": 320
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.6993464052287581,
|
| 2254 |
+
"grad_norm": 1.8325444459915161,
|
| 2255 |
+
"learning_rate": 9.302832244008714e-07,
|
| 2256 |
+
"loss": 4.202396869659424,
|
| 2257 |
+
"step": 321
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.7015250544662309,
|
| 2261 |
+
"grad_norm": 3.0213937759399414,
|
| 2262 |
+
"learning_rate": 9.300653594771241e-07,
|
| 2263 |
+
"loss": 4.599020481109619,
|
| 2264 |
+
"step": 322
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.7037037037037037,
|
| 2268 |
+
"grad_norm": 2.5810821056365967,
|
| 2269 |
+
"learning_rate": 9.298474945533769e-07,
|
| 2270 |
+
"loss": 4.495166778564453,
|
| 2271 |
+
"step": 323
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.7058823529411765,
|
| 2275 |
+
"grad_norm": 1.9636465311050415,
|
| 2276 |
+
"learning_rate": 9.296296296296295e-07,
|
| 2277 |
+
"loss": 4.338723659515381,
|
| 2278 |
+
"step": 324
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.7080610021786492,
|
| 2282 |
+
"grad_norm": 2.700573682785034,
|
| 2283 |
+
"learning_rate": 9.294117647058824e-07,
|
| 2284 |
+
"loss": 4.1468682289123535,
|
| 2285 |
+
"step": 325
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.710239651416122,
|
| 2289 |
+
"grad_norm": 2.126833438873291,
|
| 2290 |
+
"learning_rate": 9.29193899782135e-07,
|
| 2291 |
+
"loss": 4.13951301574707,
|
| 2292 |
+
"step": 326
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.7124183006535948,
|
| 2296 |
+
"grad_norm": 2.4611458778381348,
|
| 2297 |
+
"learning_rate": 9.289760348583878e-07,
|
| 2298 |
+
"loss": 4.541684150695801,
|
| 2299 |
+
"step": 327
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.7145969498910676,
|
| 2303 |
+
"grad_norm": 1.6345309019088745,
|
| 2304 |
+
"learning_rate": 9.287581699346405e-07,
|
| 2305 |
+
"loss": 4.199406147003174,
|
| 2306 |
+
"step": 328
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.7167755991285403,
|
| 2310 |
+
"grad_norm": 2.4470903873443604,
|
| 2311 |
+
"learning_rate": 9.285403050108932e-07,
|
| 2312 |
+
"loss": 4.442519664764404,
|
| 2313 |
+
"step": 329
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.7189542483660131,
|
| 2317 |
+
"grad_norm": 2.8630640506744385,
|
| 2318 |
+
"learning_rate": 9.283224400871459e-07,
|
| 2319 |
+
"loss": 4.423019886016846,
|
| 2320 |
+
"step": 330
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.7211328976034859,
|
| 2324 |
+
"grad_norm": 2.1433722972869873,
|
| 2325 |
+
"learning_rate": 9.281045751633987e-07,
|
| 2326 |
+
"loss": 4.492217540740967,
|
| 2327 |
+
"step": 331
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.7233115468409586,
|
| 2331 |
+
"grad_norm": 2.396273136138916,
|
| 2332 |
+
"learning_rate": 9.278867102396514e-07,
|
| 2333 |
+
"loss": 4.223300457000732,
|
| 2334 |
+
"step": 332
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.7254901960784313,
|
| 2338 |
+
"grad_norm": 2.381741523742676,
|
| 2339 |
+
"learning_rate": 9.276688453159041e-07,
|
| 2340 |
+
"loss": 4.33833122253418,
|
| 2341 |
+
"step": 333
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.7276688453159041,
|
| 2345 |
+
"grad_norm": 1.8426613807678223,
|
| 2346 |
+
"learning_rate": 9.274509803921568e-07,
|
| 2347 |
+
"loss": 4.187051296234131,
|
| 2348 |
+
"step": 334
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.7298474945533769,
|
| 2352 |
+
"grad_norm": 2.631394624710083,
|
| 2353 |
+
"learning_rate": 9.272331154684096e-07,
|
| 2354 |
+
"loss": 4.438161373138428,
|
| 2355 |
+
"step": 335
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.7320261437908496,
|
| 2359 |
+
"grad_norm": 2.438077926635742,
|
| 2360 |
+
"learning_rate": 9.270152505446622e-07,
|
| 2361 |
+
"loss": 4.312593460083008,
|
| 2362 |
+
"step": 336
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.7342047930283224,
|
| 2366 |
+
"grad_norm": 3.4880318641662598,
|
| 2367 |
+
"learning_rate": 9.267973856209151e-07,
|
| 2368 |
+
"loss": 4.550225257873535,
|
| 2369 |
+
"step": 337
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.7363834422657952,
|
| 2373 |
+
"grad_norm": 1.809789776802063,
|
| 2374 |
+
"learning_rate": 9.265795206971677e-07,
|
| 2375 |
+
"loss": 4.273606300354004,
|
| 2376 |
+
"step": 338
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.738562091503268,
|
| 2380 |
+
"grad_norm": 1.7368791103363037,
|
| 2381 |
+
"learning_rate": 9.263616557734205e-07,
|
| 2382 |
+
"loss": 4.258157253265381,
|
| 2383 |
+
"step": 339
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.7407407407407407,
|
| 2387 |
+
"grad_norm": 3.2504823207855225,
|
| 2388 |
+
"learning_rate": 9.261437908496732e-07,
|
| 2389 |
+
"loss": 4.630444526672363,
|
| 2390 |
+
"step": 340
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.7429193899782135,
|
| 2394 |
+
"grad_norm": 2.2657594680786133,
|
| 2395 |
+
"learning_rate": 9.259259259259259e-07,
|
| 2396 |
+
"loss": 4.2488203048706055,
|
| 2397 |
+
"step": 341
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.7450980392156863,
|
| 2401 |
+
"grad_norm": 1.7225124835968018,
|
| 2402 |
+
"learning_rate": 9.257080610021786e-07,
|
| 2403 |
+
"loss": 4.161405563354492,
|
| 2404 |
+
"step": 342
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.7472766884531591,
|
| 2408 |
+
"grad_norm": 2.4991836547851562,
|
| 2409 |
+
"learning_rate": 9.254901960784314e-07,
|
| 2410 |
+
"loss": 4.285762310028076,
|
| 2411 |
+
"step": 343
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.7494553376906318,
|
| 2415 |
+
"grad_norm": 2.18890643119812,
|
| 2416 |
+
"learning_rate": 9.252723311546841e-07,
|
| 2417 |
+
"loss": 4.175844192504883,
|
| 2418 |
+
"step": 344
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.7516339869281046,
|
| 2422 |
+
"grad_norm": 2.609976053237915,
|
| 2423 |
+
"learning_rate": 9.250544662309368e-07,
|
| 2424 |
+
"loss": 4.452181816101074,
|
| 2425 |
+
"step": 345
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.7538126361655774,
|
| 2429 |
+
"grad_norm": 3.713862419128418,
|
| 2430 |
+
"learning_rate": 9.248366013071895e-07,
|
| 2431 |
+
"loss": 4.6298112869262695,
|
| 2432 |
+
"step": 346
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.7559912854030502,
|
| 2436 |
+
"grad_norm": 2.2569708824157715,
|
| 2437 |
+
"learning_rate": 9.246187363834423e-07,
|
| 2438 |
+
"loss": 4.350952625274658,
|
| 2439 |
+
"step": 347
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.7581699346405228,
|
| 2443 |
+
"grad_norm": 1.7120873928070068,
|
| 2444 |
+
"learning_rate": 9.244008714596949e-07,
|
| 2445 |
+
"loss": 4.095013618469238,
|
| 2446 |
+
"step": 348
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.7603485838779956,
|
| 2450 |
+
"grad_norm": 1.9212177991867065,
|
| 2451 |
+
"learning_rate": 9.241830065359478e-07,
|
| 2452 |
+
"loss": 4.035152435302734,
|
| 2453 |
+
"step": 349
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.7625272331154684,
|
| 2457 |
+
"grad_norm": 2.2976410388946533,
|
| 2458 |
+
"learning_rate": 9.239651416122004e-07,
|
| 2459 |
+
"loss": 4.412503719329834,
|
| 2460 |
+
"step": 350
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.7647058823529411,
|
| 2464 |
+
"grad_norm": 1.9677550792694092,
|
| 2465 |
+
"learning_rate": 9.23747276688453e-07,
|
| 2466 |
+
"loss": 4.223837375640869,
|
| 2467 |
+
"step": 351
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.7668845315904139,
|
| 2471 |
+
"grad_norm": 2.0862555503845215,
|
| 2472 |
+
"learning_rate": 9.235294117647059e-07,
|
| 2473 |
+
"loss": 4.148982524871826,
|
| 2474 |
+
"step": 352
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.7690631808278867,
|
| 2478 |
+
"grad_norm": 2.399984836578369,
|
| 2479 |
+
"learning_rate": 9.233115468409585e-07,
|
| 2480 |
+
"loss": 4.187849998474121,
|
| 2481 |
+
"step": 353
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.7712418300653595,
|
| 2485 |
+
"grad_norm": 2.9156839847564697,
|
| 2486 |
+
"learning_rate": 9.230936819172113e-07,
|
| 2487 |
+
"loss": 4.528846263885498,
|
| 2488 |
+
"step": 354
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.7734204793028322,
|
| 2492 |
+
"grad_norm": 1.7015364170074463,
|
| 2493 |
+
"learning_rate": 9.22875816993464e-07,
|
| 2494 |
+
"loss": 4.217906951904297,
|
| 2495 |
+
"step": 355
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.775599128540305,
|
| 2499 |
+
"grad_norm": 1.6197303533554077,
|
| 2500 |
+
"learning_rate": 9.226579520697168e-07,
|
| 2501 |
+
"loss": 4.077565670013428,
|
| 2502 |
+
"step": 356
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.7777777777777778,
|
| 2506 |
+
"grad_norm": 1.6793276071548462,
|
| 2507 |
+
"learning_rate": 9.224400871459694e-07,
|
| 2508 |
+
"loss": 4.178196430206299,
|
| 2509 |
+
"step": 357
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.7799564270152506,
|
| 2513 |
+
"grad_norm": 2.427659511566162,
|
| 2514 |
+
"learning_rate": 9.222222222222222e-07,
|
| 2515 |
+
"loss": 4.2796711921691895,
|
| 2516 |
+
"step": 358
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.7821350762527233,
|
| 2520 |
+
"grad_norm": 2.461893081665039,
|
| 2521 |
+
"learning_rate": 9.220043572984749e-07,
|
| 2522 |
+
"loss": 4.355025291442871,
|
| 2523 |
+
"step": 359
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.7843137254901961,
|
| 2527 |
+
"grad_norm": 2.247121810913086,
|
| 2528 |
+
"learning_rate": 9.217864923747276e-07,
|
| 2529 |
+
"loss": 4.3149285316467285,
|
| 2530 |
+
"step": 360
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.7864923747276689,
|
| 2534 |
+
"grad_norm": 1.7950170040130615,
|
| 2535 |
+
"learning_rate": 9.215686274509803e-07,
|
| 2536 |
+
"loss": 4.239467144012451,
|
| 2537 |
+
"step": 361
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.7886710239651417,
|
| 2541 |
+
"grad_norm": 1.9137388467788696,
|
| 2542 |
+
"learning_rate": 9.213507625272331e-07,
|
| 2543 |
+
"loss": 4.354663848876953,
|
| 2544 |
+
"step": 362
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.7908496732026143,
|
| 2548 |
+
"grad_norm": 2.1859757900238037,
|
| 2549 |
+
"learning_rate": 9.211328976034857e-07,
|
| 2550 |
+
"loss": 4.221486568450928,
|
| 2551 |
+
"step": 363
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.7930283224400871,
|
| 2555 |
+
"grad_norm": 2.097460985183716,
|
| 2556 |
+
"learning_rate": 9.209150326797385e-07,
|
| 2557 |
+
"loss": 4.222695827484131,
|
| 2558 |
+
"step": 364
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.7952069716775599,
|
| 2562 |
+
"grad_norm": 2.1484479904174805,
|
| 2563 |
+
"learning_rate": 9.206971677559912e-07,
|
| 2564 |
+
"loss": 4.170539379119873,
|
| 2565 |
+
"step": 365
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.7973856209150327,
|
| 2569 |
+
"grad_norm": 1.9138914346694946,
|
| 2570 |
+
"learning_rate": 9.20479302832244e-07,
|
| 2571 |
+
"loss": 4.183845043182373,
|
| 2572 |
+
"step": 366
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.7995642701525054,
|
| 2576 |
+
"grad_norm": 2.649709939956665,
|
| 2577 |
+
"learning_rate": 9.202614379084966e-07,
|
| 2578 |
+
"loss": 4.5764617919921875,
|
| 2579 |
+
"step": 367
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.8017429193899782,
|
| 2583 |
+
"grad_norm": 2.4475293159484863,
|
| 2584 |
+
"learning_rate": 9.200435729847495e-07,
|
| 2585 |
+
"loss": 4.32996129989624,
|
| 2586 |
+
"step": 368
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.803921568627451,
|
| 2590 |
+
"grad_norm": 2.343046188354492,
|
| 2591 |
+
"learning_rate": 9.198257080610021e-07,
|
| 2592 |
+
"loss": 4.385317325592041,
|
| 2593 |
+
"step": 369
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.8061002178649237,
|
| 2597 |
+
"grad_norm": 1.8386296033859253,
|
| 2598 |
+
"learning_rate": 9.196078431372548e-07,
|
| 2599 |
+
"loss": 4.227548599243164,
|
| 2600 |
+
"step": 370
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.8082788671023965,
|
| 2604 |
+
"grad_norm": 1.614132046699524,
|
| 2605 |
+
"learning_rate": 9.193899782135076e-07,
|
| 2606 |
+
"loss": 4.114497184753418,
|
| 2607 |
+
"step": 371
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.8104575163398693,
|
| 2611 |
+
"grad_norm": 1.7535715103149414,
|
| 2612 |
+
"learning_rate": 9.191721132897603e-07,
|
| 2613 |
+
"loss": 4.214768409729004,
|
| 2614 |
+
"step": 372
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.8126361655773421,
|
| 2618 |
+
"grad_norm": 2.0214993953704834,
|
| 2619 |
+
"learning_rate": 9.18954248366013e-07,
|
| 2620 |
+
"loss": 4.2975263595581055,
|
| 2621 |
+
"step": 373
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.8148148148148148,
|
| 2625 |
+
"grad_norm": 2.0663769245147705,
|
| 2626 |
+
"learning_rate": 9.187363834422658e-07,
|
| 2627 |
+
"loss": 4.2605438232421875,
|
| 2628 |
+
"step": 374
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.8169934640522876,
|
| 2632 |
+
"grad_norm": 1.6967873573303223,
|
| 2633 |
+
"learning_rate": 9.185185185185184e-07,
|
| 2634 |
+
"loss": 4.128928184509277,
|
| 2635 |
+
"step": 375
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.8191721132897604,
|
| 2639 |
+
"grad_norm": 1.8438379764556885,
|
| 2640 |
+
"learning_rate": 9.183006535947712e-07,
|
| 2641 |
+
"loss": 4.261013984680176,
|
| 2642 |
+
"step": 376
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.8213507625272332,
|
| 2646 |
+
"grad_norm": 2.049132823944092,
|
| 2647 |
+
"learning_rate": 9.180827886710239e-07,
|
| 2648 |
+
"loss": 4.306873798370361,
|
| 2649 |
+
"step": 377
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.8235294117647058,
|
| 2653 |
+
"grad_norm": 1.8627986907958984,
|
| 2654 |
+
"learning_rate": 9.178649237472767e-07,
|
| 2655 |
+
"loss": 4.302986145019531,
|
| 2656 |
+
"step": 378
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.8257080610021786,
|
| 2660 |
+
"grad_norm": 1.6413536071777344,
|
| 2661 |
+
"learning_rate": 9.176470588235293e-07,
|
| 2662 |
+
"loss": 4.1943793296813965,
|
| 2663 |
+
"step": 379
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.8278867102396514,
|
| 2667 |
+
"grad_norm": 1.7843068838119507,
|
| 2668 |
+
"learning_rate": 9.174291938997822e-07,
|
| 2669 |
+
"loss": 4.1645684242248535,
|
| 2670 |
+
"step": 380
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.8300653594771242,
|
| 2674 |
+
"grad_norm": 2.0969436168670654,
|
| 2675 |
+
"learning_rate": 9.172113289760348e-07,
|
| 2676 |
+
"loss": 4.049801826477051,
|
| 2677 |
+
"step": 381
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.8322440087145969,
|
| 2681 |
+
"grad_norm": 2.387089967727661,
|
| 2682 |
+
"learning_rate": 9.169934640522875e-07,
|
| 2683 |
+
"loss": 4.419530391693115,
|
| 2684 |
+
"step": 382
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.8344226579520697,
|
| 2688 |
+
"grad_norm": 1.9397732019424438,
|
| 2689 |
+
"learning_rate": 9.167755991285403e-07,
|
| 2690 |
+
"loss": 4.22908353805542,
|
| 2691 |
+
"step": 383
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.8366013071895425,
|
| 2695 |
+
"grad_norm": 1.7454991340637207,
|
| 2696 |
+
"learning_rate": 9.16557734204793e-07,
|
| 2697 |
+
"loss": 4.344266891479492,
|
| 2698 |
+
"step": 384
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.8387799564270153,
|
| 2702 |
+
"grad_norm": 1.9364548921585083,
|
| 2703 |
+
"learning_rate": 9.163398692810457e-07,
|
| 2704 |
+
"loss": 4.270198345184326,
|
| 2705 |
+
"step": 385
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.840958605664488,
|
| 2709 |
+
"grad_norm": 2.5902137756347656,
|
| 2710 |
+
"learning_rate": 9.161220043572985e-07,
|
| 2711 |
+
"loss": 4.300908088684082,
|
| 2712 |
+
"step": 386
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.8431372549019608,
|
| 2716 |
+
"grad_norm": 3.546748399734497,
|
| 2717 |
+
"learning_rate": 9.159041394335511e-07,
|
| 2718 |
+
"loss": 4.561097145080566,
|
| 2719 |
+
"step": 387
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.8453159041394336,
|
| 2723 |
+
"grad_norm": 1.779766321182251,
|
| 2724 |
+
"learning_rate": 9.156862745098039e-07,
|
| 2725 |
+
"loss": 4.041597843170166,
|
| 2726 |
+
"step": 388
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.8474945533769063,
|
| 2730 |
+
"grad_norm": 1.8111950159072876,
|
| 2731 |
+
"learning_rate": 9.154684095860566e-07,
|
| 2732 |
+
"loss": 4.299168586730957,
|
| 2733 |
+
"step": 389
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.8496732026143791,
|
| 2737 |
+
"grad_norm": 2.395869016647339,
|
| 2738 |
+
"learning_rate": 9.152505446623094e-07,
|
| 2739 |
+
"loss": 4.353262424468994,
|
| 2740 |
+
"step": 390
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.8518518518518519,
|
| 2744 |
+
"grad_norm": 2.060559034347534,
|
| 2745 |
+
"learning_rate": 9.15032679738562e-07,
|
| 2746 |
+
"loss": 4.2379302978515625,
|
| 2747 |
+
"step": 391
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.8540305010893247,
|
| 2751 |
+
"grad_norm": 2.1842563152313232,
|
| 2752 |
+
"learning_rate": 9.148148148148148e-07,
|
| 2753 |
+
"loss": 4.31560754776001,
|
| 2754 |
+
"step": 392
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.8562091503267973,
|
| 2758 |
+
"grad_norm": 1.7702100276947021,
|
| 2759 |
+
"learning_rate": 9.145969498910675e-07,
|
| 2760 |
+
"loss": 4.2212018966674805,
|
| 2761 |
+
"step": 393
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.8583877995642701,
|
| 2765 |
+
"grad_norm": 3.1450130939483643,
|
| 2766 |
+
"learning_rate": 9.143790849673202e-07,
|
| 2767 |
+
"loss": 4.469844341278076,
|
| 2768 |
+
"step": 394
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.8605664488017429,
|
| 2772 |
+
"grad_norm": 2.660785436630249,
|
| 2773 |
+
"learning_rate": 9.14161220043573e-07,
|
| 2774 |
+
"loss": 4.3779296875,
|
| 2775 |
+
"step": 395
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.8627450980392157,
|
| 2779 |
+
"grad_norm": 1.6954896450042725,
|
| 2780 |
+
"learning_rate": 9.139433551198257e-07,
|
| 2781 |
+
"loss": 4.254485607147217,
|
| 2782 |
+
"step": 396
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.8649237472766884,
|
| 2786 |
+
"grad_norm": 2.3023900985717773,
|
| 2787 |
+
"learning_rate": 9.137254901960783e-07,
|
| 2788 |
+
"loss": 4.345731258392334,
|
| 2789 |
+
"step": 397
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.8671023965141612,
|
| 2793 |
+
"grad_norm": 2.0327610969543457,
|
| 2794 |
+
"learning_rate": 9.135076252723312e-07,
|
| 2795 |
+
"loss": 4.395279407501221,
|
| 2796 |
+
"step": 398
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.869281045751634,
|
| 2800 |
+
"grad_norm": 2.6276464462280273,
|
| 2801 |
+
"learning_rate": 9.132897603485838e-07,
|
| 2802 |
+
"loss": 4.379213333129883,
|
| 2803 |
+
"step": 399
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.8714596949891068,
|
| 2807 |
+
"grad_norm": 2.8123104572296143,
|
| 2808 |
+
"learning_rate": 9.130718954248366e-07,
|
| 2809 |
+
"loss": 4.4300079345703125,
|
| 2810 |
+
"step": 400
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.8736383442265795,
|
| 2814 |
+
"grad_norm": 1.9245363473892212,
|
| 2815 |
+
"learning_rate": 9.128540305010893e-07,
|
| 2816 |
+
"loss": 4.219707012176514,
|
| 2817 |
+
"step": 401
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.8758169934640523,
|
| 2821 |
+
"grad_norm": 1.8081426620483398,
|
| 2822 |
+
"learning_rate": 9.126361655773421e-07,
|
| 2823 |
+
"loss": 4.338159561157227,
|
| 2824 |
+
"step": 402
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.8779956427015251,
|
| 2828 |
+
"grad_norm": 2.749330520629883,
|
| 2829 |
+
"learning_rate": 9.124183006535947e-07,
|
| 2830 |
+
"loss": 4.506350517272949,
|
| 2831 |
+
"step": 403
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.8801742919389978,
|
| 2835 |
+
"grad_norm": 1.4844481945037842,
|
| 2836 |
+
"learning_rate": 9.122004357298475e-07,
|
| 2837 |
+
"loss": 4.188736438751221,
|
| 2838 |
+
"step": 404
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.8823529411764706,
|
| 2842 |
+
"grad_norm": 2.186659336090088,
|
| 2843 |
+
"learning_rate": 9.119825708061002e-07,
|
| 2844 |
+
"loss": 4.305603981018066,
|
| 2845 |
+
"step": 405
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.8845315904139434,
|
| 2849 |
+
"grad_norm": 2.066389322280884,
|
| 2850 |
+
"learning_rate": 9.117647058823529e-07,
|
| 2851 |
+
"loss": 4.277411937713623,
|
| 2852 |
+
"step": 406
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.8867102396514162,
|
| 2856 |
+
"grad_norm": 1.9937480688095093,
|
| 2857 |
+
"learning_rate": 9.115468409586057e-07,
|
| 2858 |
+
"loss": 4.248752593994141,
|
| 2859 |
+
"step": 407
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.8888888888888888,
|
| 2863 |
+
"grad_norm": 2.5236587524414062,
|
| 2864 |
+
"learning_rate": 9.113289760348584e-07,
|
| 2865 |
+
"loss": 4.383094310760498,
|
| 2866 |
+
"step": 408
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.8910675381263616,
|
| 2870 |
+
"grad_norm": 2.0782392024993896,
|
| 2871 |
+
"learning_rate": 9.11111111111111e-07,
|
| 2872 |
+
"loss": 4.37091588973999,
|
| 2873 |
+
"step": 409
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.8932461873638344,
|
| 2877 |
+
"grad_norm": 2.1633827686309814,
|
| 2878 |
+
"learning_rate": 9.108932461873638e-07,
|
| 2879 |
+
"loss": 4.201651096343994,
|
| 2880 |
+
"step": 410
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.8954248366013072,
|
| 2884 |
+
"grad_norm": 2.063110589981079,
|
| 2885 |
+
"learning_rate": 9.106753812636165e-07,
|
| 2886 |
+
"loss": 4.328912734985352,
|
| 2887 |
+
"step": 411
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 0.8976034858387799,
|
| 2891 |
+
"grad_norm": 2.8345420360565186,
|
| 2892 |
+
"learning_rate": 9.104575163398693e-07,
|
| 2893 |
+
"loss": 4.280642032623291,
|
| 2894 |
+
"step": 412
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.8997821350762527,
|
| 2898 |
+
"grad_norm": 2.138573169708252,
|
| 2899 |
+
"learning_rate": 9.102396514161219e-07,
|
| 2900 |
+
"loss": 4.277536392211914,
|
| 2901 |
+
"step": 413
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 0.9019607843137255,
|
| 2905 |
+
"grad_norm": 2.5910751819610596,
|
| 2906 |
+
"learning_rate": 9.100217864923748e-07,
|
| 2907 |
+
"loss": 4.363705158233643,
|
| 2908 |
+
"step": 414
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 0.9041394335511983,
|
| 2912 |
+
"grad_norm": 2.3000571727752686,
|
| 2913 |
+
"learning_rate": 9.098039215686274e-07,
|
| 2914 |
+
"loss": 4.293865203857422,
|
| 2915 |
+
"step": 415
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 0.906318082788671,
|
| 2919 |
+
"grad_norm": 1.9352879524230957,
|
| 2920 |
+
"learning_rate": 9.0958605664488e-07,
|
| 2921 |
+
"loss": 4.306790351867676,
|
| 2922 |
+
"step": 416
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 0.9084967320261438,
|
| 2926 |
+
"grad_norm": 2.054032564163208,
|
| 2927 |
+
"learning_rate": 9.093681917211329e-07,
|
| 2928 |
+
"loss": 4.107227325439453,
|
| 2929 |
+
"step": 417
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 0.9106753812636166,
|
| 2933 |
+
"grad_norm": 2.259209632873535,
|
| 2934 |
+
"learning_rate": 9.091503267973855e-07,
|
| 2935 |
+
"loss": 4.391446113586426,
|
| 2936 |
+
"step": 418
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.9128540305010894,
|
| 2940 |
+
"grad_norm": 2.0108606815338135,
|
| 2941 |
+
"learning_rate": 9.089324618736383e-07,
|
| 2942 |
+
"loss": 4.246882915496826,
|
| 2943 |
+
"step": 419
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 0.9150326797385621,
|
| 2947 |
+
"grad_norm": 2.10844349861145,
|
| 2948 |
+
"learning_rate": 9.08714596949891e-07,
|
| 2949 |
+
"loss": 4.255201816558838,
|
| 2950 |
+
"step": 420
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 0.9172113289760349,
|
| 2954 |
+
"grad_norm": 2.282139539718628,
|
| 2955 |
+
"learning_rate": 9.084967320261437e-07,
|
| 2956 |
+
"loss": 4.2623724937438965,
|
| 2957 |
+
"step": 421
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.9193899782135077,
|
| 2961 |
+
"grad_norm": 3.288189172744751,
|
| 2962 |
+
"learning_rate": 9.082788671023964e-07,
|
| 2963 |
+
"loss": 4.55091667175293,
|
| 2964 |
+
"step": 422
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.9215686274509803,
|
| 2968 |
+
"grad_norm": 2.574491500854492,
|
| 2969 |
+
"learning_rate": 9.080610021786492e-07,
|
| 2970 |
+
"loss": 4.347263813018799,
|
| 2971 |
+
"step": 423
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.9237472766884531,
|
| 2975 |
+
"grad_norm": 2.54724383354187,
|
| 2976 |
+
"learning_rate": 9.078431372549019e-07,
|
| 2977 |
+
"loss": 4.444369316101074,
|
| 2978 |
+
"step": 424
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.9259259259259259,
|
| 2982 |
+
"grad_norm": 2.2615246772766113,
|
| 2983 |
+
"learning_rate": 9.076252723311546e-07,
|
| 2984 |
+
"loss": 4.327207565307617,
|
| 2985 |
+
"step": 425
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 0.9281045751633987,
|
| 2989 |
+
"grad_norm": 2.0451500415802,
|
| 2990 |
+
"learning_rate": 9.074074074074074e-07,
|
| 2991 |
+
"loss": 4.299535751342773,
|
| 2992 |
+
"step": 426
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 0.9302832244008714,
|
| 2996 |
+
"grad_norm": 1.9952106475830078,
|
| 2997 |
+
"learning_rate": 9.071895424836601e-07,
|
| 2998 |
+
"loss": 4.185388565063477,
|
| 2999 |
+
"step": 427
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 0.9324618736383442,
|
| 3003 |
+
"grad_norm": 1.6416575908660889,
|
| 3004 |
+
"learning_rate": 9.069716775599127e-07,
|
| 3005 |
+
"loss": 4.195568084716797,
|
| 3006 |
+
"step": 428
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 0.934640522875817,
|
| 3010 |
+
"grad_norm": 2.031949281692505,
|
| 3011 |
+
"learning_rate": 9.067538126361656e-07,
|
| 3012 |
+
"loss": 4.262988567352295,
|
| 3013 |
+
"step": 429
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 0.9368191721132898,
|
| 3017 |
+
"grad_norm": 2.343195676803589,
|
| 3018 |
+
"learning_rate": 9.065359477124182e-07,
|
| 3019 |
+
"loss": 4.361613750457764,
|
| 3020 |
+
"step": 430
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.9389978213507625,
|
| 3024 |
+
"grad_norm": 2.6240570545196533,
|
| 3025 |
+
"learning_rate": 9.06318082788671e-07,
|
| 3026 |
+
"loss": 4.398077964782715,
|
| 3027 |
+
"step": 431
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 0.9411764705882353,
|
| 3031 |
+
"grad_norm": 2.5013344287872314,
|
| 3032 |
+
"learning_rate": 9.061002178649237e-07,
|
| 3033 |
+
"loss": 4.313061237335205,
|
| 3034 |
+
"step": 432
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 0.9433551198257081,
|
| 3038 |
+
"grad_norm": 1.6849699020385742,
|
| 3039 |
+
"learning_rate": 9.058823529411764e-07,
|
| 3040 |
+
"loss": 3.9826457500457764,
|
| 3041 |
+
"step": 433
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 0.9455337690631809,
|
| 3045 |
+
"grad_norm": 2.4513988494873047,
|
| 3046 |
+
"learning_rate": 9.056644880174291e-07,
|
| 3047 |
+
"loss": 4.215115547180176,
|
| 3048 |
+
"step": 434
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 0.9477124183006536,
|
| 3052 |
+
"grad_norm": 1.684166669845581,
|
| 3053 |
+
"learning_rate": 9.054466230936819e-07,
|
| 3054 |
+
"loss": 4.183655261993408,
|
| 3055 |
+
"step": 435
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 0.9498910675381264,
|
| 3059 |
+
"grad_norm": 1.5734747648239136,
|
| 3060 |
+
"learning_rate": 9.052287581699346e-07,
|
| 3061 |
+
"loss": 4.135869979858398,
|
| 3062 |
+
"step": 436
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.9520697167755992,
|
| 3066 |
+
"grad_norm": 3.9758388996124268,
|
| 3067 |
+
"learning_rate": 9.050108932461873e-07,
|
| 3068 |
+
"loss": 4.34391450881958,
|
| 3069 |
+
"step": 437
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.954248366013072,
|
| 3073 |
+
"grad_norm": 1.9097188711166382,
|
| 3074 |
+
"learning_rate": 9.0479302832244e-07,
|
| 3075 |
+
"loss": 4.253366947174072,
|
| 3076 |
+
"step": 438
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.9564270152505446,
|
| 3080 |
+
"grad_norm": 1.6577128171920776,
|
| 3081 |
+
"learning_rate": 9.045751633986928e-07,
|
| 3082 |
+
"loss": 4.1301469802856445,
|
| 3083 |
+
"step": 439
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 0.9586056644880174,
|
| 3087 |
+
"grad_norm": 2.240204334259033,
|
| 3088 |
+
"learning_rate": 9.043572984749454e-07,
|
| 3089 |
+
"loss": 4.202823162078857,
|
| 3090 |
+
"step": 440
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 0.9607843137254902,
|
| 3094 |
+
"grad_norm": 2.3804500102996826,
|
| 3095 |
+
"learning_rate": 9.041394335511983e-07,
|
| 3096 |
+
"loss": 4.424624919891357,
|
| 3097 |
+
"step": 441
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.9629629629629629,
|
| 3101 |
+
"grad_norm": 2.0912375450134277,
|
| 3102 |
+
"learning_rate": 9.039215686274509e-07,
|
| 3103 |
+
"loss": 4.134670257568359,
|
| 3104 |
+
"step": 442
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.9651416122004357,
|
| 3108 |
+
"grad_norm": 1.5136829614639282,
|
| 3109 |
+
"learning_rate": 9.037037037037037e-07,
|
| 3110 |
+
"loss": 4.028146743774414,
|
| 3111 |
+
"step": 443
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 0.9673202614379085,
|
| 3115 |
+
"grad_norm": 1.9006588459014893,
|
| 3116 |
+
"learning_rate": 9.034858387799564e-07,
|
| 3117 |
+
"loss": 4.248746871948242,
|
| 3118 |
+
"step": 444
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 0.9694989106753813,
|
| 3122 |
+
"grad_norm": 1.9264826774597168,
|
| 3123 |
+
"learning_rate": 9.032679738562091e-07,
|
| 3124 |
+
"loss": 4.300281047821045,
|
| 3125 |
+
"step": 445
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 0.971677559912854,
|
| 3129 |
+
"grad_norm": 2.325807571411133,
|
| 3130 |
+
"learning_rate": 9.030501089324618e-07,
|
| 3131 |
+
"loss": 4.411880016326904,
|
| 3132 |
+
"step": 446
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 0.9738562091503268,
|
| 3136 |
+
"grad_norm": 2.2446606159210205,
|
| 3137 |
+
"learning_rate": 9.028322440087146e-07,
|
| 3138 |
+
"loss": 4.300230979919434,
|
| 3139 |
+
"step": 447
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 0.9760348583877996,
|
| 3143 |
+
"grad_norm": 1.8679618835449219,
|
| 3144 |
+
"learning_rate": 9.026143790849673e-07,
|
| 3145 |
+
"loss": 4.216586589813232,
|
| 3146 |
+
"step": 448
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.9782135076252724,
|
| 3150 |
+
"grad_norm": 2.71272349357605,
|
| 3151 |
+
"learning_rate": 9.0239651416122e-07,
|
| 3152 |
+
"loss": 4.361291885375977,
|
| 3153 |
+
"step": 449
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 0.9803921568627451,
|
| 3157 |
+
"grad_norm": 1.8621163368225098,
|
| 3158 |
+
"learning_rate": 9.021786492374727e-07,
|
| 3159 |
+
"loss": 4.023743629455566,
|
| 3160 |
+
"step": 450
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 0.9825708061002179,
|
| 3164 |
+
"grad_norm": 2.2548575401306152,
|
| 3165 |
+
"learning_rate": 9.019607843137255e-07,
|
| 3166 |
+
"loss": 4.341646671295166,
|
| 3167 |
+
"step": 451
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 0.9847494553376906,
|
| 3171 |
+
"grad_norm": 1.8140944242477417,
|
| 3172 |
+
"learning_rate": 9.017429193899781e-07,
|
| 3173 |
+
"loss": 4.2807183265686035,
|
| 3174 |
+
"step": 452
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 0.9869281045751634,
|
| 3178 |
+
"grad_norm": 2.296813726425171,
|
| 3179 |
+
"learning_rate": 9.01525054466231e-07,
|
| 3180 |
+
"loss": 4.189460277557373,
|
| 3181 |
+
"step": 453
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 0.9891067538126361,
|
| 3185 |
+
"grad_norm": 1.9771134853363037,
|
| 3186 |
+
"learning_rate": 9.013071895424836e-07,
|
| 3187 |
+
"loss": 4.273813247680664,
|
| 3188 |
+
"step": 454
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.9912854030501089,
|
| 3192 |
+
"grad_norm": 2.457392454147339,
|
| 3193 |
+
"learning_rate": 9.010893246187364e-07,
|
| 3194 |
+
"loss": 4.328354835510254,
|
| 3195 |
+
"step": 455
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 0.9934640522875817,
|
| 3199 |
+
"grad_norm": 2.8040881156921387,
|
| 3200 |
+
"learning_rate": 9.00871459694989e-07,
|
| 3201 |
+
"loss": 4.24334716796875,
|
| 3202 |
+
"step": 456
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 0.9956427015250545,
|
| 3206 |
+
"grad_norm": 2.514680862426758,
|
| 3207 |
+
"learning_rate": 9.006535947712418e-07,
|
| 3208 |
+
"loss": 4.360405921936035,
|
| 3209 |
+
"step": 457
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 0.9978213507625272,
|
| 3213 |
+
"grad_norm": 2.3096747398376465,
|
| 3214 |
+
"learning_rate": 9.004357298474945e-07,
|
| 3215 |
+
"loss": 4.383677005767822,
|
| 3216 |
+
"step": 458
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 1.0,
|
| 3220 |
+
"grad_norm": 1.7039768695831299,
|
| 3221 |
+
"learning_rate": 9.002178649237472e-07,
|
| 3222 |
+
"loss": 4.212360858917236,
|
| 3223 |
+
"step": 459
|
| 3224 |
+
}
|
| 3225 |
+
],
|
| 3226 |
+
"logging_steps": 1,
|
| 3227 |
+
"max_steps": 4590,
|
| 3228 |
+
"num_input_tokens_seen": 0,
|
| 3229 |
+
"num_train_epochs": 10,
|
| 3230 |
+
"save_steps": 1000000000000,
|
| 3231 |
+
"stateful_callbacks": {
|
| 3232 |
+
"TrainerControl": {
|
| 3233 |
+
"args": {
|
| 3234 |
+
"should_epoch_stop": false,
|
| 3235 |
+
"should_evaluate": false,
|
| 3236 |
+
"should_log": false,
|
| 3237 |
+
"should_save": true,
|
| 3238 |
+
"should_training_stop": false
|
| 3239 |
+
},
|
| 3240 |
+
"attributes": {}
|
| 3241 |
+
}
|
| 3242 |
+
},
|
| 3243 |
+
"total_flos": 1.7952635964616704e+16,
|
| 3244 |
+
"train_batch_size": 2,
|
| 3245 |
+
"trial_name": null,
|
| 3246 |
+
"trial_params": null
|
| 3247 |
+
}
|
checkpoint-459/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fb9b3902bc563e4e6de6717ae2840117d1cad8b6e05f1ce75c4d95b603d82f9
|
| 3 |
+
size 5201
|