Training in progress, step 2500, checkpoint
Browse files- checkpoint-2500/README.md +202 -0
- checkpoint-2500/adapter_config.json +34 -0
- checkpoint-2500/adapter_model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state_0.pth +3 -0
- checkpoint-2500/rng_state_1.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +34 -0
- checkpoint-2500/tokenizer.model +3 -0
- checkpoint-2500/tokenizer_config.json +72 -0
- checkpoint-2500/trainer_state.json +571 -0
- checkpoint-2500/training_args.bin +3 -0
checkpoint-2500/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/gemma-7b-bnb-4bit
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-2500/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/gemma-7b-bnb-4bit",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 8,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": "unsloth",
|
22 |
+
"target_modules": [
|
23 |
+
"down_proj",
|
24 |
+
"o_proj",
|
25 |
+
"up_proj",
|
26 |
+
"q_proj",
|
27 |
+
"v_proj",
|
28 |
+
"k_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-2500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:377123a5ea4efaf0374e9d1866ccf9fa43e4bf98309c1aa9ca19005c5bfe4e0a
|
3 |
+
size 100059752
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1d6e3f7a90523b30a93d8533c0ae3c5b316eda1aff34a809a9c021ac66bd43e
|
3 |
+
size 50541492
|
checkpoint-2500/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9784d223de06f5a58f5d2011ae392c217bbcc5a226663b3dd5e4a0023a88b58e
|
3 |
+
size 14512
|
checkpoint-2500/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40a92f4e108b6f171a9f3eb8de7a52ed0002816d15b36e92ba905856910d502e
|
3 |
+
size 14512
|
checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b87b6187de3329a93c64b60c534f255d54d935892922aff23368fcc34b34ff6a
|
3 |
+
size 1192
|
checkpoint-2500/special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<bos>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
checkpoint-2500/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
checkpoint-2500/tokenizer_config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"106": {
|
38 |
+
"content": "<start_of_turn>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"107": {
|
46 |
+
"content": "<end_of_turn>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<start_of_turn>",
|
56 |
+
"<end_of_turn>"
|
57 |
+
],
|
58 |
+
"bos_token": "<bos>",
|
59 |
+
"chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\\n' + content + '\\n\\n### Response:\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<eos>' + '\\n\\n' }}{% endif %}{% endfor %}",
|
60 |
+
"clean_up_tokenization_spaces": false,
|
61 |
+
"eos_token": "<eos>",
|
62 |
+
"legacy": null,
|
63 |
+
"model_max_length": 1000000000000000019884624838656,
|
64 |
+
"pad_token": "<pad>",
|
65 |
+
"padding_side": "right",
|
66 |
+
"sp_model_kwargs": {},
|
67 |
+
"spaces_between_special_tokens": false,
|
68 |
+
"split_special_tokens": false,
|
69 |
+
"tokenizer_class": "GemmaTokenizer",
|
70 |
+
"unk_token": "<unk>",
|
71 |
+
"use_default_system_prompt": false
|
72 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
@@ -0,0 +1,571 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.8768367767333984,
|
3 |
+
"best_model_checkpoint": "/kaggle/working/gemma/checkpoint-1600",
|
4 |
+
"epoch": 0.983477576711251,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 2500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 2.6322383880615234,
|
14 |
+
"learning_rate": 0.0003,
|
15 |
+
"loss": 4.1999,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04,
|
20 |
+
"grad_norm": 1.3033926486968994,
|
21 |
+
"learning_rate": 0.0003,
|
22 |
+
"loss": 2.1859,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.04,
|
27 |
+
"eval_loss": 2.0820870399475098,
|
28 |
+
"eval_runtime": 110.3393,
|
29 |
+
"eval_samples_per_second": 0.933,
|
30 |
+
"eval_steps_per_second": 0.236,
|
31 |
+
"step": 100
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.06,
|
35 |
+
"grad_norm": 1.6072160005569458,
|
36 |
+
"learning_rate": 0.0003,
|
37 |
+
"loss": 2.1419,
|
38 |
+
"step": 150
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.08,
|
42 |
+
"grad_norm": 1.4586890935897827,
|
43 |
+
"learning_rate": 0.0003,
|
44 |
+
"loss": 2.1001,
|
45 |
+
"step": 200
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.08,
|
49 |
+
"eval_loss": 1.99821937084198,
|
50 |
+
"eval_runtime": 110.16,
|
51 |
+
"eval_samples_per_second": 0.935,
|
52 |
+
"eval_steps_per_second": 0.236,
|
53 |
+
"step": 200
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.1,
|
57 |
+
"grad_norm": 1.309139370918274,
|
58 |
+
"learning_rate": 0.0003,
|
59 |
+
"loss": 2.0746,
|
60 |
+
"step": 250
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.12,
|
64 |
+
"grad_norm": 1.487611174583435,
|
65 |
+
"learning_rate": 0.0003,
|
66 |
+
"loss": 2.0647,
|
67 |
+
"step": 300
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.12,
|
71 |
+
"eval_loss": 1.9572771787643433,
|
72 |
+
"eval_runtime": 109.5937,
|
73 |
+
"eval_samples_per_second": 0.94,
|
74 |
+
"eval_steps_per_second": 0.237,
|
75 |
+
"step": 300
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.14,
|
79 |
+
"grad_norm": 1.494892954826355,
|
80 |
+
"learning_rate": 0.0003,
|
81 |
+
"loss": 2.0195,
|
82 |
+
"step": 350
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.16,
|
86 |
+
"grad_norm": 1.4196828603744507,
|
87 |
+
"learning_rate": 0.0003,
|
88 |
+
"loss": 2.0195,
|
89 |
+
"step": 400
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.16,
|
93 |
+
"eval_loss": 1.9236102104187012,
|
94 |
+
"eval_runtime": 109.859,
|
95 |
+
"eval_samples_per_second": 0.938,
|
96 |
+
"eval_steps_per_second": 0.237,
|
97 |
+
"step": 400
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.18,
|
101 |
+
"grad_norm": 1.7659281492233276,
|
102 |
+
"learning_rate": 0.0003,
|
103 |
+
"loss": 1.9753,
|
104 |
+
"step": 450
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.2,
|
108 |
+
"grad_norm": 1.059668779373169,
|
109 |
+
"learning_rate": 0.0003,
|
110 |
+
"loss": 1.9975,
|
111 |
+
"step": 500
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.2,
|
115 |
+
"eval_loss": 1.9109984636306763,
|
116 |
+
"eval_runtime": 109.5777,
|
117 |
+
"eval_samples_per_second": 0.94,
|
118 |
+
"eval_steps_per_second": 0.237,
|
119 |
+
"step": 500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.22,
|
123 |
+
"grad_norm": 1.3529094457626343,
|
124 |
+
"learning_rate": 0.0003,
|
125 |
+
"loss": 1.9846,
|
126 |
+
"step": 550
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 0.24,
|
130 |
+
"grad_norm": 1.4471253156661987,
|
131 |
+
"learning_rate": 0.0003,
|
132 |
+
"loss": 1.9809,
|
133 |
+
"step": 600
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.24,
|
137 |
+
"eval_loss": 1.9085875749588013,
|
138 |
+
"eval_runtime": 109.6643,
|
139 |
+
"eval_samples_per_second": 0.939,
|
140 |
+
"eval_steps_per_second": 0.237,
|
141 |
+
"step": 600
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.26,
|
145 |
+
"grad_norm": 1.965285301208496,
|
146 |
+
"learning_rate": 0.0003,
|
147 |
+
"loss": 2.0156,
|
148 |
+
"step": 650
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.28,
|
152 |
+
"grad_norm": 1.1004948616027832,
|
153 |
+
"learning_rate": 0.0003,
|
154 |
+
"loss": 2.0118,
|
155 |
+
"step": 700
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.28,
|
159 |
+
"eval_loss": 1.9014776945114136,
|
160 |
+
"eval_runtime": 109.9343,
|
161 |
+
"eval_samples_per_second": 0.937,
|
162 |
+
"eval_steps_per_second": 0.237,
|
163 |
+
"step": 700
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.3,
|
167 |
+
"grad_norm": 1.5002790689468384,
|
168 |
+
"learning_rate": 0.0003,
|
169 |
+
"loss": 1.9538,
|
170 |
+
"step": 750
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.31,
|
174 |
+
"grad_norm": 1.2678498029708862,
|
175 |
+
"learning_rate": 0.0003,
|
176 |
+
"loss": 1.9402,
|
177 |
+
"step": 800
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.31,
|
181 |
+
"eval_loss": 1.8954542875289917,
|
182 |
+
"eval_runtime": 110.006,
|
183 |
+
"eval_samples_per_second": 0.936,
|
184 |
+
"eval_steps_per_second": 0.236,
|
185 |
+
"step": 800
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.33,
|
189 |
+
"grad_norm": 1.2786470651626587,
|
190 |
+
"learning_rate": 0.0003,
|
191 |
+
"loss": 1.9687,
|
192 |
+
"step": 850
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.35,
|
196 |
+
"grad_norm": 1.6264179944992065,
|
197 |
+
"learning_rate": 0.0003,
|
198 |
+
"loss": 1.9531,
|
199 |
+
"step": 900
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.35,
|
203 |
+
"eval_loss": 1.8900243043899536,
|
204 |
+
"eval_runtime": 110.1408,
|
205 |
+
"eval_samples_per_second": 0.935,
|
206 |
+
"eval_steps_per_second": 0.236,
|
207 |
+
"step": 900
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.37,
|
211 |
+
"grad_norm": 1.2318661212921143,
|
212 |
+
"learning_rate": 0.0003,
|
213 |
+
"loss": 1.9663,
|
214 |
+
"step": 950
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.39,
|
218 |
+
"grad_norm": 1.4853723049163818,
|
219 |
+
"learning_rate": 0.0003,
|
220 |
+
"loss": 1.9804,
|
221 |
+
"step": 1000
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.39,
|
225 |
+
"eval_loss": 1.896203875541687,
|
226 |
+
"eval_runtime": 109.686,
|
227 |
+
"eval_samples_per_second": 0.939,
|
228 |
+
"eval_steps_per_second": 0.237,
|
229 |
+
"step": 1000
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.41,
|
233 |
+
"grad_norm": 1.1880249977111816,
|
234 |
+
"learning_rate": 0.0003,
|
235 |
+
"loss": 1.9693,
|
236 |
+
"step": 1050
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.43,
|
240 |
+
"grad_norm": 2.1265156269073486,
|
241 |
+
"learning_rate": 0.0003,
|
242 |
+
"loss": 1.9953,
|
243 |
+
"step": 1100
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.43,
|
247 |
+
"eval_loss": 1.8932738304138184,
|
248 |
+
"eval_runtime": 109.7941,
|
249 |
+
"eval_samples_per_second": 0.938,
|
250 |
+
"eval_steps_per_second": 0.237,
|
251 |
+
"step": 1100
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.45,
|
255 |
+
"grad_norm": 2.2788913249969482,
|
256 |
+
"learning_rate": 0.0003,
|
257 |
+
"loss": 1.9427,
|
258 |
+
"step": 1150
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 0.47,
|
262 |
+
"grad_norm": 1.2446949481964111,
|
263 |
+
"learning_rate": 0.0003,
|
264 |
+
"loss": 1.9435,
|
265 |
+
"step": 1200
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.47,
|
269 |
+
"eval_loss": 1.891483187675476,
|
270 |
+
"eval_runtime": 109.743,
|
271 |
+
"eval_samples_per_second": 0.939,
|
272 |
+
"eval_steps_per_second": 0.237,
|
273 |
+
"step": 1200
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.49,
|
277 |
+
"grad_norm": 1.5069431066513062,
|
278 |
+
"learning_rate": 0.0003,
|
279 |
+
"loss": 1.9891,
|
280 |
+
"step": 1250
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.51,
|
284 |
+
"grad_norm": 1.3292410373687744,
|
285 |
+
"learning_rate": 0.0003,
|
286 |
+
"loss": 1.9804,
|
287 |
+
"step": 1300
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.51,
|
291 |
+
"eval_loss": 1.8822150230407715,
|
292 |
+
"eval_runtime": 109.7975,
|
293 |
+
"eval_samples_per_second": 0.938,
|
294 |
+
"eval_steps_per_second": 0.237,
|
295 |
+
"step": 1300
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.53,
|
299 |
+
"grad_norm": 1.274938941001892,
|
300 |
+
"learning_rate": 0.0003,
|
301 |
+
"loss": 1.9754,
|
302 |
+
"step": 1350
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.55,
|
306 |
+
"grad_norm": 1.5717120170593262,
|
307 |
+
"learning_rate": 0.0003,
|
308 |
+
"loss": 1.9758,
|
309 |
+
"step": 1400
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.55,
|
313 |
+
"eval_loss": 1.8797138929367065,
|
314 |
+
"eval_runtime": 109.9298,
|
315 |
+
"eval_samples_per_second": 0.937,
|
316 |
+
"eval_steps_per_second": 0.237,
|
317 |
+
"step": 1400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.57,
|
321 |
+
"grad_norm": 1.445812463760376,
|
322 |
+
"learning_rate": 0.0003,
|
323 |
+
"loss": 1.9378,
|
324 |
+
"step": 1450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.59,
|
328 |
+
"grad_norm": 1.3848668336868286,
|
329 |
+
"learning_rate": 0.0003,
|
330 |
+
"loss": 1.9472,
|
331 |
+
"step": 1500
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.59,
|
335 |
+
"eval_loss": 1.8788877725601196,
|
336 |
+
"eval_runtime": 109.275,
|
337 |
+
"eval_samples_per_second": 0.943,
|
338 |
+
"eval_steps_per_second": 0.238,
|
339 |
+
"step": 1500
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.61,
|
343 |
+
"grad_norm": 1.536832332611084,
|
344 |
+
"learning_rate": 0.0003,
|
345 |
+
"loss": 1.9483,
|
346 |
+
"step": 1550
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.63,
|
350 |
+
"grad_norm": 1.37943696975708,
|
351 |
+
"learning_rate": 0.0003,
|
352 |
+
"loss": 1.9507,
|
353 |
+
"step": 1600
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.63,
|
357 |
+
"eval_loss": 1.8768367767333984,
|
358 |
+
"eval_runtime": 109.2487,
|
359 |
+
"eval_samples_per_second": 0.943,
|
360 |
+
"eval_steps_per_second": 0.238,
|
361 |
+
"step": 1600
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.65,
|
365 |
+
"grad_norm": 1.1901755332946777,
|
366 |
+
"learning_rate": 0.0003,
|
367 |
+
"loss": 1.9402,
|
368 |
+
"step": 1650
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.67,
|
372 |
+
"grad_norm": 1.0710890293121338,
|
373 |
+
"learning_rate": 0.0003,
|
374 |
+
"loss": 1.9488,
|
375 |
+
"step": 1700
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.67,
|
379 |
+
"eval_loss": 1.884979009628296,
|
380 |
+
"eval_runtime": 109.08,
|
381 |
+
"eval_samples_per_second": 0.944,
|
382 |
+
"eval_steps_per_second": 0.238,
|
383 |
+
"step": 1700
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.69,
|
387 |
+
"grad_norm": 1.2577444314956665,
|
388 |
+
"learning_rate": 0.0003,
|
389 |
+
"loss": 1.9571,
|
390 |
+
"step": 1750
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.71,
|
394 |
+
"grad_norm": 2.273926258087158,
|
395 |
+
"learning_rate": 0.0003,
|
396 |
+
"loss": 1.9708,
|
397 |
+
"step": 1800
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.71,
|
401 |
+
"eval_loss": 1.8852429389953613,
|
402 |
+
"eval_runtime": 109.1066,
|
403 |
+
"eval_samples_per_second": 0.944,
|
404 |
+
"eval_steps_per_second": 0.238,
|
405 |
+
"step": 1800
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.73,
|
409 |
+
"grad_norm": 1.308111548423767,
|
410 |
+
"learning_rate": 0.0003,
|
411 |
+
"loss": 1.989,
|
412 |
+
"step": 1850
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 0.75,
|
416 |
+
"grad_norm": 1.5021519660949707,
|
417 |
+
"learning_rate": 0.0003,
|
418 |
+
"loss": 1.9692,
|
419 |
+
"step": 1900
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.75,
|
423 |
+
"eval_loss": 1.8924355506896973,
|
424 |
+
"eval_runtime": 108.9102,
|
425 |
+
"eval_samples_per_second": 0.946,
|
426 |
+
"eval_steps_per_second": 0.239,
|
427 |
+
"step": 1900
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.77,
|
431 |
+
"grad_norm": 1.4355289936065674,
|
432 |
+
"learning_rate": 0.0003,
|
433 |
+
"loss": 1.948,
|
434 |
+
"step": 1950
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.79,
|
438 |
+
"grad_norm": 1.268176794052124,
|
439 |
+
"learning_rate": 0.0003,
|
440 |
+
"loss": 1.9708,
|
441 |
+
"step": 2000
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.79,
|
445 |
+
"eval_loss": 1.8840947151184082,
|
446 |
+
"eval_runtime": 109.0758,
|
447 |
+
"eval_samples_per_second": 0.944,
|
448 |
+
"eval_steps_per_second": 0.238,
|
449 |
+
"step": 2000
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.81,
|
453 |
+
"grad_norm": 1.141319990158081,
|
454 |
+
"learning_rate": 0.0003,
|
455 |
+
"loss": 1.9651,
|
456 |
+
"step": 2050
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 0.83,
|
460 |
+
"grad_norm": 1.4737452268600464,
|
461 |
+
"learning_rate": 0.0003,
|
462 |
+
"loss": 1.976,
|
463 |
+
"step": 2100
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 0.83,
|
467 |
+
"eval_loss": 1.8879451751708984,
|
468 |
+
"eval_runtime": 109.5286,
|
469 |
+
"eval_samples_per_second": 0.94,
|
470 |
+
"eval_steps_per_second": 0.237,
|
471 |
+
"step": 2100
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.85,
|
475 |
+
"grad_norm": 1.5503915548324585,
|
476 |
+
"learning_rate": 0.0003,
|
477 |
+
"loss": 1.9487,
|
478 |
+
"step": 2150
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.87,
|
482 |
+
"grad_norm": 1.513409972190857,
|
483 |
+
"learning_rate": 0.0003,
|
484 |
+
"loss": 1.9337,
|
485 |
+
"step": 2200
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.87,
|
489 |
+
"eval_loss": 1.8889082670211792,
|
490 |
+
"eval_runtime": 109.4713,
|
491 |
+
"eval_samples_per_second": 0.941,
|
492 |
+
"eval_steps_per_second": 0.238,
|
493 |
+
"step": 2200
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.89,
|
497 |
+
"grad_norm": 1.676282525062561,
|
498 |
+
"learning_rate": 0.0003,
|
499 |
+
"loss": 1.9467,
|
500 |
+
"step": 2250
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.9,
|
504 |
+
"grad_norm": 1.3259328603744507,
|
505 |
+
"learning_rate": 0.0003,
|
506 |
+
"loss": 1.9542,
|
507 |
+
"step": 2300
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.9,
|
511 |
+
"eval_loss": 1.8862982988357544,
|
512 |
+
"eval_runtime": 109.095,
|
513 |
+
"eval_samples_per_second": 0.944,
|
514 |
+
"eval_steps_per_second": 0.238,
|
515 |
+
"step": 2300
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.92,
|
519 |
+
"grad_norm": 1.5091557502746582,
|
520 |
+
"learning_rate": 0.0003,
|
521 |
+
"loss": 1.9526,
|
522 |
+
"step": 2350
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.94,
|
526 |
+
"grad_norm": 1.378811240196228,
|
527 |
+
"learning_rate": 0.0003,
|
528 |
+
"loss": 1.9778,
|
529 |
+
"step": 2400
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.94,
|
533 |
+
"eval_loss": 1.8892956972122192,
|
534 |
+
"eval_runtime": 109.3468,
|
535 |
+
"eval_samples_per_second": 0.942,
|
536 |
+
"eval_steps_per_second": 0.238,
|
537 |
+
"step": 2400
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.96,
|
541 |
+
"grad_norm": 1.6397453546524048,
|
542 |
+
"learning_rate": 0.0003,
|
543 |
+
"loss": 1.9613,
|
544 |
+
"step": 2450
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.98,
|
548 |
+
"grad_norm": 1.437840223312378,
|
549 |
+
"learning_rate": 0.0003,
|
550 |
+
"loss": 1.9696,
|
551 |
+
"step": 2500
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.98,
|
555 |
+
"eval_loss": 1.8877886533737183,
|
556 |
+
"eval_runtime": 109.3923,
|
557 |
+
"eval_samples_per_second": 0.942,
|
558 |
+
"eval_steps_per_second": 0.238,
|
559 |
+
"step": 2500
|
560 |
+
}
|
561 |
+
],
|
562 |
+
"logging_steps": 50,
|
563 |
+
"max_steps": 12710,
|
564 |
+
"num_input_tokens_seen": 0,
|
565 |
+
"num_train_epochs": 5,
|
566 |
+
"save_steps": 100,
|
567 |
+
"total_flos": 2.1043649680769024e+18,
|
568 |
+
"train_batch_size": 2,
|
569 |
+
"trial_name": null,
|
570 |
+
"trial_params": null
|
571 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aa6a145827ab3567f8d35dec10f844e10312812d3470e09d369a923854ee9fe
|
3 |
+
size 5112
|