ToastyPigeon
commited on
Commit
•
b613126
1
Parent(s):
2b44816
Training in progress, step 293, checkpoint
Browse files- checkpoint-293/README.md +202 -0
- checkpoint-293/adapter_config.json +34 -0
- checkpoint-293/adapter_model.safetensors +3 -0
- checkpoint-293/optimizer.pt +3 -0
- checkpoint-293/rng_state.pth +3 -0
- checkpoint-293/scheduler.pt +3 -0
- checkpoint-293/special_tokens_map.json +30 -0
- checkpoint-293/tokenizer.json +0 -0
- checkpoint-293/tokenizer_config.json +0 -0
- checkpoint-293/trainer_state.json +2164 -0
- checkpoint-293/training_args.bin +3 -0
checkpoint-293/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: mistralai/Mistral-Nemo-Instruct-2407
|
3 |
+
library_name: peft
|
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 0.11.1
|
checkpoint-293/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
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": 128,
|
14 |
+
"lora_dropout": 0.125,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"up_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-293/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e3cbf0b9531af98ab133c478dd478062563ec2e83ad646422a25a9c44b2a3a9
|
3 |
+
size 456206712
|
checkpoint-293/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d836c0e8b20a07c3a803815bf296158dce35ea36e4dc795a71ede3c9e5e988f7
|
3 |
+
size 457678740
|
checkpoint-293/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db71d068329ef30a6aa7807040f181e2648d7c7599e4b074821335c705688255
|
3 |
+
size 14244
|
checkpoint-293/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e9b868c7da7d3274a833e5f6b57ba48c69e01a57ef377ddadd53ceda7c2cdcc
|
3 |
+
size 1064
|
checkpoint-293/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-293/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-293/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-293/trainer_state.json
ADDED
@@ -0,0 +1,2164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5008547008547009,
|
5 |
+
"eval_steps": 30,
|
6 |
+
"global_step": 293,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0017094017094017094,
|
13 |
+
"grad_norm": 0.640625,
|
14 |
+
"learning_rate": 1.5e-06,
|
15 |
+
"loss": 2.347,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0017094017094017094,
|
20 |
+
"eval_loss": 2.301453113555908,
|
21 |
+
"eval_runtime": 86.8185,
|
22 |
+
"eval_samples_per_second": 2.949,
|
23 |
+
"eval_steps_per_second": 0.495,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.003418803418803419,
|
28 |
+
"grad_norm": 0.64453125,
|
29 |
+
"learning_rate": 3e-06,
|
30 |
+
"loss": 2.3765,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.005128205128205128,
|
35 |
+
"grad_norm": 0.66015625,
|
36 |
+
"learning_rate": 4.5e-06,
|
37 |
+
"loss": 2.4015,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.006837606837606838,
|
42 |
+
"grad_norm": 0.6953125,
|
43 |
+
"learning_rate": 6e-06,
|
44 |
+
"loss": 2.307,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.008547008547008548,
|
49 |
+
"grad_norm": 0.67578125,
|
50 |
+
"learning_rate": 7.5e-06,
|
51 |
+
"loss": 2.4666,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.010256410256410256,
|
56 |
+
"grad_norm": 0.96484375,
|
57 |
+
"learning_rate": 9e-06,
|
58 |
+
"loss": 2.3027,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.011965811965811967,
|
63 |
+
"grad_norm": 0.6171875,
|
64 |
+
"learning_rate": 1.05e-05,
|
65 |
+
"loss": 2.4554,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.013675213675213675,
|
70 |
+
"grad_norm": 0.64453125,
|
71 |
+
"learning_rate": 1.2e-05,
|
72 |
+
"loss": 2.4017,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.015384615384615385,
|
77 |
+
"grad_norm": 0.57421875,
|
78 |
+
"learning_rate": 1.3500000000000001e-05,
|
79 |
+
"loss": 2.3931,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.017094017094017096,
|
84 |
+
"grad_norm": 1.0703125,
|
85 |
+
"learning_rate": 1.5e-05,
|
86 |
+
"loss": 2.3904,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.018803418803418803,
|
91 |
+
"grad_norm": 1.359375,
|
92 |
+
"learning_rate": 1.65e-05,
|
93 |
+
"loss": 2.4122,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.020512820512820513,
|
98 |
+
"grad_norm": 0.5078125,
|
99 |
+
"learning_rate": 1.8e-05,
|
100 |
+
"loss": 2.2968,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.022222222222222223,
|
105 |
+
"grad_norm": 0.76953125,
|
106 |
+
"learning_rate": 1.95e-05,
|
107 |
+
"loss": 2.3248,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.023931623931623933,
|
112 |
+
"grad_norm": 0.85546875,
|
113 |
+
"learning_rate": 2.1e-05,
|
114 |
+
"loss": 2.3328,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.02564102564102564,
|
119 |
+
"grad_norm": 0.58203125,
|
120 |
+
"learning_rate": 2.25e-05,
|
121 |
+
"loss": 2.3261,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.02735042735042735,
|
126 |
+
"grad_norm": 0.7109375,
|
127 |
+
"learning_rate": 2.4e-05,
|
128 |
+
"loss": 2.3912,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.02905982905982906,
|
133 |
+
"grad_norm": 0.58203125,
|
134 |
+
"learning_rate": 2.55e-05,
|
135 |
+
"loss": 2.2254,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.03076923076923077,
|
140 |
+
"grad_norm": 0.58203125,
|
141 |
+
"learning_rate": 2.7000000000000002e-05,
|
142 |
+
"loss": 2.3051,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.03247863247863248,
|
147 |
+
"grad_norm": 0.54296875,
|
148 |
+
"learning_rate": 2.8499999999999998e-05,
|
149 |
+
"loss": 2.266,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.03418803418803419,
|
154 |
+
"grad_norm": 0.54296875,
|
155 |
+
"learning_rate": 3e-05,
|
156 |
+
"loss": 2.2876,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.035897435897435895,
|
161 |
+
"grad_norm": 0.5078125,
|
162 |
+
"learning_rate": 2.99997797141509e-05,
|
163 |
+
"loss": 2.3568,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.037606837606837605,
|
168 |
+
"grad_norm": 0.60546875,
|
169 |
+
"learning_rate": 2.9999118863414234e-05,
|
170 |
+
"loss": 2.37,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.039316239316239315,
|
175 |
+
"grad_norm": 0.515625,
|
176 |
+
"learning_rate": 2.9998017468221747e-05,
|
177 |
+
"loss": 2.2132,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.041025641025641026,
|
182 |
+
"grad_norm": 0.54296875,
|
183 |
+
"learning_rate": 2.9996475562625607e-05,
|
184 |
+
"loss": 2.3333,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.042735042735042736,
|
189 |
+
"grad_norm": 0.51171875,
|
190 |
+
"learning_rate": 2.9994493194297398e-05,
|
191 |
+
"loss": 2.3721,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.044444444444444446,
|
196 |
+
"grad_norm": 0.5078125,
|
197 |
+
"learning_rate": 2.999207042452661e-05,
|
198 |
+
"loss": 2.3663,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.046153846153846156,
|
203 |
+
"grad_norm": 0.5390625,
|
204 |
+
"learning_rate": 2.998920732821878e-05,
|
205 |
+
"loss": 2.2828,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.04786324786324787,
|
210 |
+
"grad_norm": 0.62890625,
|
211 |
+
"learning_rate": 2.9985903993893144e-05,
|
212 |
+
"loss": 2.2689,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.04957264957264957,
|
217 |
+
"grad_norm": 0.55078125,
|
218 |
+
"learning_rate": 2.998216052367993e-05,
|
219 |
+
"loss": 2.2138,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.05128205128205128,
|
224 |
+
"grad_norm": 0.5625,
|
225 |
+
"learning_rate": 2.9977977033317164e-05,
|
226 |
+
"loss": 2.306,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.05128205128205128,
|
231 |
+
"eval_loss": 2.2630789279937744,
|
232 |
+
"eval_runtime": 87.4474,
|
233 |
+
"eval_samples_per_second": 2.927,
|
234 |
+
"eval_steps_per_second": 0.492,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.05299145299145299,
|
239 |
+
"grad_norm": 0.515625,
|
240 |
+
"learning_rate": 2.997335365214713e-05,
|
241 |
+
"loss": 2.296,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.0547008547008547,
|
246 |
+
"grad_norm": 1.140625,
|
247 |
+
"learning_rate": 2.996829052311235e-05,
|
248 |
+
"loss": 2.3959,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.05641025641025641,
|
253 |
+
"grad_norm": 0.53125,
|
254 |
+
"learning_rate": 2.9962787802751164e-05,
|
255 |
+
"loss": 2.386,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.05811965811965812,
|
260 |
+
"grad_norm": 0.4921875,
|
261 |
+
"learning_rate": 2.9956845661192886e-05,
|
262 |
+
"loss": 2.3119,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.05982905982905983,
|
267 |
+
"grad_norm": 0.52734375,
|
268 |
+
"learning_rate": 2.9950464282152565e-05,
|
269 |
+
"loss": 2.4883,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.06153846153846154,
|
274 |
+
"grad_norm": 0.5078125,
|
275 |
+
"learning_rate": 2.9943643862925295e-05,
|
276 |
+
"loss": 2.3211,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.06324786324786325,
|
281 |
+
"grad_norm": 0.51171875,
|
282 |
+
"learning_rate": 2.9936384614380105e-05,
|
283 |
+
"loss": 2.3355,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.06495726495726496,
|
288 |
+
"grad_norm": 0.51953125,
|
289 |
+
"learning_rate": 2.992868676095344e-05,
|
290 |
+
"loss": 2.2054,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.06666666666666667,
|
295 |
+
"grad_norm": 1.28125,
|
296 |
+
"learning_rate": 2.992055054064225e-05,
|
297 |
+
"loss": 2.252,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.06837606837606838,
|
302 |
+
"grad_norm": 0.49609375,
|
303 |
+
"learning_rate": 2.9911976204996588e-05,
|
304 |
+
"loss": 2.1774,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.07008547008547009,
|
309 |
+
"grad_norm": 0.48046875,
|
310 |
+
"learning_rate": 2.990296401911187e-05,
|
311 |
+
"loss": 2.2469,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.07179487179487179,
|
316 |
+
"grad_norm": 0.52734375,
|
317 |
+
"learning_rate": 2.9893514261620653e-05,
|
318 |
+
"loss": 2.3641,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.0735042735042735,
|
323 |
+
"grad_norm": 0.49609375,
|
324 |
+
"learning_rate": 2.988362722468405e-05,
|
325 |
+
"loss": 2.2189,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.07521367521367521,
|
330 |
+
"grad_norm": 0.52734375,
|
331 |
+
"learning_rate": 2.9873303213982663e-05,
|
332 |
+
"loss": 2.2367,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.07692307692307693,
|
337 |
+
"grad_norm": 0.54296875,
|
338 |
+
"learning_rate": 2.9862542548707153e-05,
|
339 |
+
"loss": 2.2121,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.07863247863247863,
|
344 |
+
"grad_norm": 0.53125,
|
345 |
+
"learning_rate": 2.9851345561548373e-05,
|
346 |
+
"loss": 2.3132,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.08034188034188035,
|
351 |
+
"grad_norm": 0.55859375,
|
352 |
+
"learning_rate": 2.9839712598687062e-05,
|
353 |
+
"loss": 2.2336,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.08205128205128205,
|
358 |
+
"grad_norm": 0.5703125,
|
359 |
+
"learning_rate": 2.982764401978317e-05,
|
360 |
+
"loss": 2.3433,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.08376068376068375,
|
365 |
+
"grad_norm": 0.546875,
|
366 |
+
"learning_rate": 2.981514019796471e-05,
|
367 |
+
"loss": 2.2469,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.08547008547008547,
|
372 |
+
"grad_norm": 0.640625,
|
373 |
+
"learning_rate": 2.9802201519816253e-05,
|
374 |
+
"loss": 2.4495,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.08717948717948718,
|
379 |
+
"grad_norm": 0.51171875,
|
380 |
+
"learning_rate": 2.978882838536695e-05,
|
381 |
+
"loss": 2.319,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.08888888888888889,
|
386 |
+
"grad_norm": 0.5078125,
|
387 |
+
"learning_rate": 2.9775021208078166e-05,
|
388 |
+
"loss": 2.2656,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.0905982905982906,
|
393 |
+
"grad_norm": 0.5390625,
|
394 |
+
"learning_rate": 2.9760780414830717e-05,
|
395 |
+
"loss": 2.3204,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.09230769230769231,
|
400 |
+
"grad_norm": 0.50390625,
|
401 |
+
"learning_rate": 2.9746106445911658e-05,
|
402 |
+
"loss": 2.3461,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.09401709401709402,
|
407 |
+
"grad_norm": 0.51953125,
|
408 |
+
"learning_rate": 2.9730999755000654e-05,
|
409 |
+
"loss": 2.3504,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.09572649572649573,
|
414 |
+
"grad_norm": 0.515625,
|
415 |
+
"learning_rate": 2.9715460809155993e-05,
|
416 |
+
"loss": 2.235,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.09743589743589744,
|
421 |
+
"grad_norm": 0.482421875,
|
422 |
+
"learning_rate": 2.9699490088800107e-05,
|
423 |
+
"loss": 2.3713,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.09914529914529914,
|
428 |
+
"grad_norm": 0.515625,
|
429 |
+
"learning_rate": 2.968308808770475e-05,
|
430 |
+
"loss": 2.2396,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.10085470085470086,
|
435 |
+
"grad_norm": 0.57421875,
|
436 |
+
"learning_rate": 2.9666255312975704e-05,
|
437 |
+
"loss": 2.2702,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.10256410256410256,
|
442 |
+
"grad_norm": 0.5,
|
443 |
+
"learning_rate": 2.9648992285037126e-05,
|
444 |
+
"loss": 2.1792,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.10256410256410256,
|
449 |
+
"eval_loss": 2.235595941543579,
|
450 |
+
"eval_runtime": 87.3908,
|
451 |
+
"eval_samples_per_second": 2.929,
|
452 |
+
"eval_steps_per_second": 0.492,
|
453 |
+
"step": 60
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.10427350427350428,
|
457 |
+
"grad_norm": 0.5078125,
|
458 |
+
"learning_rate": 2.9631299537615433e-05,
|
459 |
+
"loss": 2.2673,
|
460 |
+
"step": 61
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.10598290598290598,
|
464 |
+
"grad_norm": 0.494140625,
|
465 |
+
"learning_rate": 2.9613177617722826e-05,
|
466 |
+
"loss": 2.1882,
|
467 |
+
"step": 62
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.1076923076923077,
|
471 |
+
"grad_norm": 0.54296875,
|
472 |
+
"learning_rate": 2.9594627085640357e-05,
|
473 |
+
"loss": 2.201,
|
474 |
+
"step": 63
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.1094017094017094,
|
478 |
+
"grad_norm": 0.55859375,
|
479 |
+
"learning_rate": 2.957564851490061e-05,
|
480 |
+
"loss": 2.2973,
|
481 |
+
"step": 64
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.1111111111111111,
|
485 |
+
"grad_norm": 0.55078125,
|
486 |
+
"learning_rate": 2.955624249226999e-05,
|
487 |
+
"loss": 2.2497,
|
488 |
+
"step": 65
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.11282051282051282,
|
492 |
+
"grad_norm": 0.5234375,
|
493 |
+
"learning_rate": 2.9536409617730553e-05,
|
494 |
+
"loss": 2.2527,
|
495 |
+
"step": 66
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.11452991452991453,
|
499 |
+
"grad_norm": 0.55078125,
|
500 |
+
"learning_rate": 2.9516150504461473e-05,
|
501 |
+
"loss": 2.2438,
|
502 |
+
"step": 67
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.11623931623931624,
|
506 |
+
"grad_norm": 0.5234375,
|
507 |
+
"learning_rate": 2.9495465778820076e-05,
|
508 |
+
"loss": 2.2101,
|
509 |
+
"step": 68
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.11794871794871795,
|
513 |
+
"grad_norm": 0.5546875,
|
514 |
+
"learning_rate": 2.9474356080322488e-05,
|
515 |
+
"loss": 2.2613,
|
516 |
+
"step": 69
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.11965811965811966,
|
520 |
+
"grad_norm": 0.53515625,
|
521 |
+
"learning_rate": 2.945282206162384e-05,
|
522 |
+
"loss": 2.2543,
|
523 |
+
"step": 70
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.12136752136752137,
|
527 |
+
"grad_norm": 0.51953125,
|
528 |
+
"learning_rate": 2.9430864388498117e-05,
|
529 |
+
"loss": 2.1064,
|
530 |
+
"step": 71
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.12307692307692308,
|
534 |
+
"grad_norm": 0.52734375,
|
535 |
+
"learning_rate": 2.940848373981754e-05,
|
536 |
+
"loss": 2.2559,
|
537 |
+
"step": 72
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.12478632478632479,
|
541 |
+
"grad_norm": 0.5546875,
|
542 |
+
"learning_rate": 2.938568080753162e-05,
|
543 |
+
"loss": 2.4249,
|
544 |
+
"step": 73
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.1264957264957265,
|
548 |
+
"grad_norm": 0.5390625,
|
549 |
+
"learning_rate": 2.936245629664574e-05,
|
550 |
+
"loss": 2.1672,
|
551 |
+
"step": 74
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.1282051282051282,
|
555 |
+
"grad_norm": 0.51171875,
|
556 |
+
"learning_rate": 2.933881092519934e-05,
|
557 |
+
"loss": 2.1782,
|
558 |
+
"step": 75
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.12991452991452992,
|
562 |
+
"grad_norm": 0.54296875,
|
563 |
+
"learning_rate": 2.9314745424243755e-05,
|
564 |
+
"loss": 2.2672,
|
565 |
+
"step": 76
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.13162393162393163,
|
569 |
+
"grad_norm": 0.54296875,
|
570 |
+
"learning_rate": 2.9290260537819593e-05,
|
571 |
+
"loss": 2.3463,
|
572 |
+
"step": 77
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.13333333333333333,
|
576 |
+
"grad_norm": 0.52734375,
|
577 |
+
"learning_rate": 2.9265357022933717e-05,
|
578 |
+
"loss": 2.3062,
|
579 |
+
"step": 78
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.13504273504273503,
|
583 |
+
"grad_norm": 0.5625,
|
584 |
+
"learning_rate": 2.9240035649535893e-05,
|
585 |
+
"loss": 2.2582,
|
586 |
+
"step": 79
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.13675213675213677,
|
590 |
+
"grad_norm": 0.52734375,
|
591 |
+
"learning_rate": 2.921429720049491e-05,
|
592 |
+
"loss": 2.2013,
|
593 |
+
"step": 80
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.13846153846153847,
|
597 |
+
"grad_norm": 0.53515625,
|
598 |
+
"learning_rate": 2.918814247157443e-05,
|
599 |
+
"loss": 2.3769,
|
600 |
+
"step": 81
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.14017094017094017,
|
604 |
+
"grad_norm": 0.546875,
|
605 |
+
"learning_rate": 2.9161572271408383e-05,
|
606 |
+
"loss": 2.1824,
|
607 |
+
"step": 82
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 0.14188034188034188,
|
611 |
+
"grad_norm": 0.55859375,
|
612 |
+
"learning_rate": 2.913458742147594e-05,
|
613 |
+
"loss": 2.3269,
|
614 |
+
"step": 83
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.14358974358974358,
|
618 |
+
"grad_norm": 0.62109375,
|
619 |
+
"learning_rate": 2.910718875607612e-05,
|
620 |
+
"loss": 2.2811,
|
621 |
+
"step": 84
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.1452991452991453,
|
625 |
+
"grad_norm": 0.5703125,
|
626 |
+
"learning_rate": 2.9079377122302015e-05,
|
627 |
+
"loss": 2.2213,
|
628 |
+
"step": 85
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.147008547008547,
|
632 |
+
"grad_norm": 0.5390625,
|
633 |
+
"learning_rate": 2.9051153380014605e-05,
|
634 |
+
"loss": 2.179,
|
635 |
+
"step": 86
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.14871794871794872,
|
639 |
+
"grad_norm": 0.546875,
|
640 |
+
"learning_rate": 2.9022518401816118e-05,
|
641 |
+
"loss": 2.1934,
|
642 |
+
"step": 87
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.15042735042735042,
|
646 |
+
"grad_norm": 0.5234375,
|
647 |
+
"learning_rate": 2.8993473073023123e-05,
|
648 |
+
"loss": 2.379,
|
649 |
+
"step": 88
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.15213675213675212,
|
653 |
+
"grad_norm": 0.58203125,
|
654 |
+
"learning_rate": 2.8964018291639117e-05,
|
655 |
+
"loss": 2.1847,
|
656 |
+
"step": 89
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.15384615384615385,
|
660 |
+
"grad_norm": 0.5703125,
|
661 |
+
"learning_rate": 2.8934154968326777e-05,
|
662 |
+
"loss": 2.2576,
|
663 |
+
"step": 90
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.15384615384615385,
|
667 |
+
"eval_loss": 2.2298240661621094,
|
668 |
+
"eval_runtime": 87.3674,
|
669 |
+
"eval_samples_per_second": 2.93,
|
670 |
+
"eval_steps_per_second": 0.492,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.15555555555555556,
|
675 |
+
"grad_norm": 0.53515625,
|
676 |
+
"learning_rate": 2.890388402637978e-05,
|
677 |
+
"loss": 2.2151,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.15726495726495726,
|
682 |
+
"grad_norm": 0.57421875,
|
683 |
+
"learning_rate": 2.8873206401694296e-05,
|
684 |
+
"loss": 2.239,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.15897435897435896,
|
689 |
+
"grad_norm": 0.6328125,
|
690 |
+
"learning_rate": 2.8842123042740018e-05,
|
691 |
+
"loss": 2.1789,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.1606837606837607,
|
696 |
+
"grad_norm": 0.609375,
|
697 |
+
"learning_rate": 2.8810634910530858e-05,
|
698 |
+
"loss": 2.2505,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.1623931623931624,
|
703 |
+
"grad_norm": 0.55078125,
|
704 |
+
"learning_rate": 2.8778742978595237e-05,
|
705 |
+
"loss": 2.2437,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.1641025641025641,
|
710 |
+
"grad_norm": 0.6171875,
|
711 |
+
"learning_rate": 2.8746448232945957e-05,
|
712 |
+
"loss": 2.3353,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.1658119658119658,
|
717 |
+
"grad_norm": 0.62109375,
|
718 |
+
"learning_rate": 2.8713751672049763e-05,
|
719 |
+
"loss": 2.1599,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.1675213675213675,
|
724 |
+
"grad_norm": 0.59375,
|
725 |
+
"learning_rate": 2.8680654306796423e-05,
|
726 |
+
"loss": 2.1994,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.16923076923076924,
|
731 |
+
"grad_norm": 0.53515625,
|
732 |
+
"learning_rate": 2.8647157160467517e-05,
|
733 |
+
"loss": 2.1375,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.17094017094017094,
|
738 |
+
"grad_norm": 0.578125,
|
739 |
+
"learning_rate": 2.8613261268704776e-05,
|
740 |
+
"loss": 2.3547,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.17264957264957265,
|
745 |
+
"grad_norm": 0.55078125,
|
746 |
+
"learning_rate": 2.8578967679478055e-05,
|
747 |
+
"loss": 2.0798,
|
748 |
+
"step": 101
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 0.17435897435897435,
|
752 |
+
"grad_norm": 0.6171875,
|
753 |
+
"learning_rate": 2.8544277453052978e-05,
|
754 |
+
"loss": 2.3431,
|
755 |
+
"step": 102
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 0.17606837606837608,
|
759 |
+
"grad_norm": 0.55078125,
|
760 |
+
"learning_rate": 2.850919166195808e-05,
|
761 |
+
"loss": 2.1824,
|
762 |
+
"step": 103
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.17777777777777778,
|
766 |
+
"grad_norm": 0.6015625,
|
767 |
+
"learning_rate": 2.847371139095173e-05,
|
768 |
+
"loss": 2.2008,
|
769 |
+
"step": 104
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.1794871794871795,
|
773 |
+
"grad_norm": 0.5546875,
|
774 |
+
"learning_rate": 2.8437837736988546e-05,
|
775 |
+
"loss": 2.238,
|
776 |
+
"step": 105
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.1811965811965812,
|
780 |
+
"grad_norm": 0.5859375,
|
781 |
+
"learning_rate": 2.8401571809185472e-05,
|
782 |
+
"loss": 2.2602,
|
783 |
+
"step": 106
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.1829059829059829,
|
787 |
+
"grad_norm": 0.625,
|
788 |
+
"learning_rate": 2.836491472878753e-05,
|
789 |
+
"loss": 2.196,
|
790 |
+
"step": 107
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 0.18461538461538463,
|
794 |
+
"grad_norm": 0.7578125,
|
795 |
+
"learning_rate": 2.8327867629133112e-05,
|
796 |
+
"loss": 2.1421,
|
797 |
+
"step": 108
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 0.18632478632478633,
|
801 |
+
"grad_norm": 0.5859375,
|
802 |
+
"learning_rate": 2.8290431655618965e-05,
|
803 |
+
"loss": 2.1574,
|
804 |
+
"step": 109
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.18803418803418803,
|
808 |
+
"grad_norm": 0.58203125,
|
809 |
+
"learning_rate": 2.8252607965664764e-05,
|
810 |
+
"loss": 2.13,
|
811 |
+
"step": 110
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.18974358974358974,
|
815 |
+
"grad_norm": 0.60546875,
|
816 |
+
"learning_rate": 2.8214397728677342e-05,
|
817 |
+
"loss": 2.2223,
|
818 |
+
"step": 111
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.19145299145299147,
|
822 |
+
"grad_norm": 0.56640625,
|
823 |
+
"learning_rate": 2.8175802126014526e-05,
|
824 |
+
"loss": 2.2207,
|
825 |
+
"step": 112
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.19316239316239317,
|
829 |
+
"grad_norm": 0.61328125,
|
830 |
+
"learning_rate": 2.8136822350948608e-05,
|
831 |
+
"loss": 2.2286,
|
832 |
+
"step": 113
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 0.19487179487179487,
|
836 |
+
"grad_norm": 0.6171875,
|
837 |
+
"learning_rate": 2.8097459608629454e-05,
|
838 |
+
"loss": 2.2064,
|
839 |
+
"step": 114
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 0.19658119658119658,
|
843 |
+
"grad_norm": 0.5625,
|
844 |
+
"learning_rate": 2.805771511604727e-05,
|
845 |
+
"loss": 2.1825,
|
846 |
+
"step": 115
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.19829059829059828,
|
850 |
+
"grad_norm": 0.5546875,
|
851 |
+
"learning_rate": 2.8017590101994924e-05,
|
852 |
+
"loss": 2.2322,
|
853 |
+
"step": 116
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.2,
|
857 |
+
"grad_norm": 0.62890625,
|
858 |
+
"learning_rate": 2.7977085807030013e-05,
|
859 |
+
"loss": 2.2489,
|
860 |
+
"step": 117
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.20170940170940171,
|
864 |
+
"grad_norm": 0.56640625,
|
865 |
+
"learning_rate": 2.793620348343647e-05,
|
866 |
+
"loss": 2.3559,
|
867 |
+
"step": 118
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.20341880341880342,
|
871 |
+
"grad_norm": 0.578125,
|
872 |
+
"learning_rate": 2.789494439518584e-05,
|
873 |
+
"loss": 2.126,
|
874 |
+
"step": 119
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.20512820512820512,
|
878 |
+
"grad_norm": 0.578125,
|
879 |
+
"learning_rate": 2.7853309817898244e-05,
|
880 |
+
"loss": 2.1577,
|
881 |
+
"step": 120
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 0.20512820512820512,
|
885 |
+
"eval_loss": 2.2236061096191406,
|
886 |
+
"eval_runtime": 87.3684,
|
887 |
+
"eval_samples_per_second": 2.93,
|
888 |
+
"eval_steps_per_second": 0.492,
|
889 |
+
"step": 120
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.20683760683760682,
|
893 |
+
"grad_norm": 0.61328125,
|
894 |
+
"learning_rate": 2.7811301038802903e-05,
|
895 |
+
"loss": 2.3332,
|
896 |
+
"step": 121
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.20854700854700856,
|
900 |
+
"grad_norm": 0.578125,
|
901 |
+
"learning_rate": 2.776891935669836e-05,
|
902 |
+
"loss": 2.279,
|
903 |
+
"step": 122
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.21025641025641026,
|
907 |
+
"grad_norm": 0.56640625,
|
908 |
+
"learning_rate": 2.77261660819123e-05,
|
909 |
+
"loss": 2.2138,
|
910 |
+
"step": 123
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 0.21196581196581196,
|
914 |
+
"grad_norm": 0.5703125,
|
915 |
+
"learning_rate": 2.7683042536261066e-05,
|
916 |
+
"loss": 2.1529,
|
917 |
+
"step": 124
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 0.21367521367521367,
|
921 |
+
"grad_norm": 0.5625,
|
922 |
+
"learning_rate": 2.763955005300879e-05,
|
923 |
+
"loss": 2.2875,
|
924 |
+
"step": 125
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.2153846153846154,
|
928 |
+
"grad_norm": 0.59765625,
|
929 |
+
"learning_rate": 2.7595689976826144e-05,
|
930 |
+
"loss": 2.1927,
|
931 |
+
"step": 126
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"epoch": 0.2170940170940171,
|
935 |
+
"grad_norm": 0.6171875,
|
936 |
+
"learning_rate": 2.755146366374879e-05,
|
937 |
+
"loss": 2.2004,
|
938 |
+
"step": 127
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.2188034188034188,
|
942 |
+
"grad_norm": 0.60546875,
|
943 |
+
"learning_rate": 2.7506872481135472e-05,
|
944 |
+
"loss": 2.1822,
|
945 |
+
"step": 128
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.2205128205128205,
|
949 |
+
"grad_norm": 0.578125,
|
950 |
+
"learning_rate": 2.7461917807625683e-05,
|
951 |
+
"loss": 2.1571,
|
952 |
+
"step": 129
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.2222222222222222,
|
956 |
+
"grad_norm": 0.58203125,
|
957 |
+
"learning_rate": 2.741660103309711e-05,
|
958 |
+
"loss": 2.2019,
|
959 |
+
"step": 130
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 0.22393162393162394,
|
963 |
+
"grad_norm": 1.015625,
|
964 |
+
"learning_rate": 2.7370923558622608e-05,
|
965 |
+
"loss": 2.2128,
|
966 |
+
"step": 131
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 0.22564102564102564,
|
970 |
+
"grad_norm": 1.2421875,
|
971 |
+
"learning_rate": 2.7324886796426928e-05,
|
972 |
+
"loss": 2.1621,
|
973 |
+
"step": 132
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"epoch": 0.22735042735042735,
|
977 |
+
"grad_norm": 0.63671875,
|
978 |
+
"learning_rate": 2.7278492169843002e-05,
|
979 |
+
"loss": 2.1667,
|
980 |
+
"step": 133
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.22905982905982905,
|
984 |
+
"grad_norm": 0.58203125,
|
985 |
+
"learning_rate": 2.723174111326799e-05,
|
986 |
+
"loss": 2.1954,
|
987 |
+
"step": 134
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.23076923076923078,
|
991 |
+
"grad_norm": 0.61328125,
|
992 |
+
"learning_rate": 2.71846350721189e-05,
|
993 |
+
"loss": 2.2353,
|
994 |
+
"step": 135
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.23247863247863249,
|
998 |
+
"grad_norm": 0.59375,
|
999 |
+
"learning_rate": 2.7137175502787905e-05,
|
1000 |
+
"loss": 2.1927,
|
1001 |
+
"step": 136
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 0.2341880341880342,
|
1005 |
+
"grad_norm": 0.609375,
|
1006 |
+
"learning_rate": 2.708936387259733e-05,
|
1007 |
+
"loss": 2.3303,
|
1008 |
+
"step": 137
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 0.2358974358974359,
|
1012 |
+
"grad_norm": 0.625,
|
1013 |
+
"learning_rate": 2.7041201659754275e-05,
|
1014 |
+
"loss": 2.2955,
|
1015 |
+
"step": 138
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 0.2376068376068376,
|
1019 |
+
"grad_norm": 0.66015625,
|
1020 |
+
"learning_rate": 2.6992690353304906e-05,
|
1021 |
+
"loss": 2.1364,
|
1022 |
+
"step": 139
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.23931623931623933,
|
1026 |
+
"grad_norm": 0.6171875,
|
1027 |
+
"learning_rate": 2.694383145308842e-05,
|
1028 |
+
"loss": 2.2165,
|
1029 |
+
"step": 140
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.24102564102564103,
|
1033 |
+
"grad_norm": 0.578125,
|
1034 |
+
"learning_rate": 2.6894626469690695e-05,
|
1035 |
+
"loss": 2.1733,
|
1036 |
+
"step": 141
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 0.24273504273504273,
|
1040 |
+
"grad_norm": 0.58984375,
|
1041 |
+
"learning_rate": 2.6845076924397558e-05,
|
1042 |
+
"loss": 2.2228,
|
1043 |
+
"step": 142
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 0.24444444444444444,
|
1047 |
+
"grad_norm": 0.625,
|
1048 |
+
"learning_rate": 2.6795184349147767e-05,
|
1049 |
+
"loss": 2.1683,
|
1050 |
+
"step": 143
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 0.24615384615384617,
|
1054 |
+
"grad_norm": 0.58203125,
|
1055 |
+
"learning_rate": 2.6744950286485654e-05,
|
1056 |
+
"loss": 2.1653,
|
1057 |
+
"step": 144
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 0.24786324786324787,
|
1061 |
+
"grad_norm": 0.6484375,
|
1062 |
+
"learning_rate": 2.66943762895134e-05,
|
1063 |
+
"loss": 2.3011,
|
1064 |
+
"step": 145
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.24957264957264957,
|
1068 |
+
"grad_norm": 0.65625,
|
1069 |
+
"learning_rate": 2.6643463921843072e-05,
|
1070 |
+
"loss": 2.1627,
|
1071 |
+
"step": 146
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.2512820512820513,
|
1075 |
+
"grad_norm": 0.5859375,
|
1076 |
+
"learning_rate": 2.659221475754822e-05,
|
1077 |
+
"loss": 2.1715,
|
1078 |
+
"step": 147
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 0.252991452991453,
|
1082 |
+
"grad_norm": 0.578125,
|
1083 |
+
"learning_rate": 2.654063038111526e-05,
|
1084 |
+
"loss": 2.1621,
|
1085 |
+
"step": 148
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 0.2547008547008547,
|
1089 |
+
"grad_norm": 0.578125,
|
1090 |
+
"learning_rate": 2.648871238739447e-05,
|
1091 |
+
"loss": 2.2397,
|
1092 |
+
"step": 149
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 0.2564102564102564,
|
1096 |
+
"grad_norm": 0.60546875,
|
1097 |
+
"learning_rate": 2.6436462381550656e-05,
|
1098 |
+
"loss": 2.1493,
|
1099 |
+
"step": 150
|
1100 |
+
},
|
1101 |
+
{
|
1102 |
+
"epoch": 0.2564102564102564,
|
1103 |
+
"eval_loss": 2.2221291065216064,
|
1104 |
+
"eval_runtime": 87.3659,
|
1105 |
+
"eval_samples_per_second": 2.93,
|
1106 |
+
"eval_steps_per_second": 0.492,
|
1107 |
+
"step": 150
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.25811965811965815,
|
1111 |
+
"grad_norm": 0.58984375,
|
1112 |
+
"learning_rate": 2.638388197901356e-05,
|
1113 |
+
"loss": 2.1664,
|
1114 |
+
"step": 151
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.25982905982905985,
|
1118 |
+
"grad_norm": 0.66015625,
|
1119 |
+
"learning_rate": 2.6330972805427904e-05,
|
1120 |
+
"loss": 2.1582,
|
1121 |
+
"step": 152
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 0.26153846153846155,
|
1125 |
+
"grad_norm": 0.578125,
|
1126 |
+
"learning_rate": 2.627773649660312e-05,
|
1127 |
+
"loss": 2.2686,
|
1128 |
+
"step": 153
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 0.26324786324786326,
|
1132 |
+
"grad_norm": 0.64453125,
|
1133 |
+
"learning_rate": 2.6224174698462793e-05,
|
1134 |
+
"loss": 2.2141,
|
1135 |
+
"step": 154
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 0.26495726495726496,
|
1139 |
+
"grad_norm": 0.66796875,
|
1140 |
+
"learning_rate": 2.617028906699375e-05,
|
1141 |
+
"loss": 2.2978,
|
1142 |
+
"step": 155
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 0.26666666666666666,
|
1146 |
+
"grad_norm": 0.5859375,
|
1147 |
+
"learning_rate": 2.611608126819488e-05,
|
1148 |
+
"loss": 2.2701,
|
1149 |
+
"step": 156
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.26837606837606837,
|
1153 |
+
"grad_norm": 0.62890625,
|
1154 |
+
"learning_rate": 2.6061552978025613e-05,
|
1155 |
+
"loss": 2.1505,
|
1156 |
+
"step": 157
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 0.27008547008547007,
|
1160 |
+
"grad_norm": 0.5859375,
|
1161 |
+
"learning_rate": 2.6006705882354133e-05,
|
1162 |
+
"loss": 2.0904,
|
1163 |
+
"step": 158
|
1164 |
+
},
|
1165 |
+
{
|
1166 |
+
"epoch": 0.2717948717948718,
|
1167 |
+
"grad_norm": 0.58203125,
|
1168 |
+
"learning_rate": 2.595154167690521e-05,
|
1169 |
+
"loss": 2.1801,
|
1170 |
+
"step": 159
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 0.27350427350427353,
|
1174 |
+
"grad_norm": 0.58984375,
|
1175 |
+
"learning_rate": 2.58960620672078e-05,
|
1176 |
+
"loss": 2.1752,
|
1177 |
+
"step": 160
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"epoch": 0.27521367521367524,
|
1181 |
+
"grad_norm": 0.59765625,
|
1182 |
+
"learning_rate": 2.5840268768542317e-05,
|
1183 |
+
"loss": 2.2138,
|
1184 |
+
"step": 161
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.27692307692307694,
|
1188 |
+
"grad_norm": 0.57421875,
|
1189 |
+
"learning_rate": 2.5784163505887594e-05,
|
1190 |
+
"loss": 1.9268,
|
1191 |
+
"step": 162
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.27863247863247864,
|
1195 |
+
"grad_norm": 0.625,
|
1196 |
+
"learning_rate": 2.5727748013867548e-05,
|
1197 |
+
"loss": 2.1888,
|
1198 |
+
"step": 163
|
1199 |
+
},
|
1200 |
+
{
|
1201 |
+
"epoch": 0.28034188034188035,
|
1202 |
+
"grad_norm": 0.58984375,
|
1203 |
+
"learning_rate": 2.5671024036697558e-05,
|
1204 |
+
"loss": 2.1613,
|
1205 |
+
"step": 164
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"epoch": 0.28205128205128205,
|
1209 |
+
"grad_norm": 0.59765625,
|
1210 |
+
"learning_rate": 2.5613993328130528e-05,
|
1211 |
+
"loss": 2.1137,
|
1212 |
+
"step": 165
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 0.28376068376068375,
|
1216 |
+
"grad_norm": 0.6328125,
|
1217 |
+
"learning_rate": 2.5556657651402683e-05,
|
1218 |
+
"loss": 2.1211,
|
1219 |
+
"step": 166
|
1220 |
+
},
|
1221 |
+
{
|
1222 |
+
"epoch": 0.28547008547008546,
|
1223 |
+
"grad_norm": 0.6171875,
|
1224 |
+
"learning_rate": 2.5499018779179032e-05,
|
1225 |
+
"loss": 2.1484,
|
1226 |
+
"step": 167
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.28717948717948716,
|
1230 |
+
"grad_norm": 0.5703125,
|
1231 |
+
"learning_rate": 2.5441078493498586e-05,
|
1232 |
+
"loss": 2.1331,
|
1233 |
+
"step": 168
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.28888888888888886,
|
1237 |
+
"grad_norm": 0.75390625,
|
1238 |
+
"learning_rate": 2.538283858571924e-05,
|
1239 |
+
"loss": 2.0982,
|
1240 |
+
"step": 169
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 0.2905982905982906,
|
1244 |
+
"grad_norm": 0.63671875,
|
1245 |
+
"learning_rate": 2.5324300856462403e-05,
|
1246 |
+
"loss": 2.1295,
|
1247 |
+
"step": 170
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 0.2923076923076923,
|
1251 |
+
"grad_norm": 0.61328125,
|
1252 |
+
"learning_rate": 2.5265467115557327e-05,
|
1253 |
+
"loss": 2.1661,
|
1254 |
+
"step": 171
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.294017094017094,
|
1258 |
+
"grad_norm": 0.6171875,
|
1259 |
+
"learning_rate": 2.5206339181985137e-05,
|
1260 |
+
"loss": 2.0045,
|
1261 |
+
"step": 172
|
1262 |
+
},
|
1263 |
+
{
|
1264 |
+
"epoch": 0.29572649572649573,
|
1265 |
+
"grad_norm": 0.61328125,
|
1266 |
+
"learning_rate": 2.5146918883822618e-05,
|
1267 |
+
"loss": 2.1627,
|
1268 |
+
"step": 173
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.29743589743589743,
|
1272 |
+
"grad_norm": 0.67578125,
|
1273 |
+
"learning_rate": 2.5087208058185676e-05,
|
1274 |
+
"loss": 2.1274,
|
1275 |
+
"step": 174
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.29914529914529914,
|
1279 |
+
"grad_norm": 0.59375,
|
1280 |
+
"learning_rate": 2.502720855117255e-05,
|
1281 |
+
"loss": 2.0704,
|
1282 |
+
"step": 175
|
1283 |
+
},
|
1284 |
+
{
|
1285 |
+
"epoch": 0.30085470085470084,
|
1286 |
+
"grad_norm": 0.62109375,
|
1287 |
+
"learning_rate": 2.4966922217806723e-05,
|
1288 |
+
"loss": 2.1342,
|
1289 |
+
"step": 176
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 0.30256410256410254,
|
1293 |
+
"grad_norm": 0.91796875,
|
1294 |
+
"learning_rate": 2.4906350921979577e-05,
|
1295 |
+
"loss": 2.0359,
|
1296 |
+
"step": 177
|
1297 |
+
},
|
1298 |
+
{
|
1299 |
+
"epoch": 0.30427350427350425,
|
1300 |
+
"grad_norm": 0.62109375,
|
1301 |
+
"learning_rate": 2.4845496536392782e-05,
|
1302 |
+
"loss": 2.1133,
|
1303 |
+
"step": 178
|
1304 |
+
},
|
1305 |
+
{
|
1306 |
+
"epoch": 0.305982905982906,
|
1307 |
+
"grad_norm": 0.6171875,
|
1308 |
+
"learning_rate": 2.4784360942500367e-05,
|
1309 |
+
"loss": 2.1915,
|
1310 |
+
"step": 179
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 0.3076923076923077,
|
1314 |
+
"grad_norm": 0.58203125,
|
1315 |
+
"learning_rate": 2.4722946030450576e-05,
|
1316 |
+
"loss": 2.1297,
|
1317 |
+
"step": 180
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 0.3076923076923077,
|
1321 |
+
"eval_loss": 2.223208427429199,
|
1322 |
+
"eval_runtime": 87.3927,
|
1323 |
+
"eval_samples_per_second": 2.929,
|
1324 |
+
"eval_steps_per_second": 0.492,
|
1325 |
+
"step": 180
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.3094017094017094,
|
1329 |
+
"grad_norm": 0.7265625,
|
1330 |
+
"learning_rate": 2.4661253699027413e-05,
|
1331 |
+
"loss": 2.0955,
|
1332 |
+
"step": 181
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.3111111111111111,
|
1336 |
+
"grad_norm": 0.67578125,
|
1337 |
+
"learning_rate": 2.459928585559195e-05,
|
1338 |
+
"loss": 2.2005,
|
1339 |
+
"step": 182
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.3128205128205128,
|
1343 |
+
"grad_norm": 0.79296875,
|
1344 |
+
"learning_rate": 2.4537044416023342e-05,
|
1345 |
+
"loss": 2.2348,
|
1346 |
+
"step": 183
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.3145299145299145,
|
1350 |
+
"grad_norm": 0.68359375,
|
1351 |
+
"learning_rate": 2.4474531304659607e-05,
|
1352 |
+
"loss": 2.1847,
|
1353 |
+
"step": 184
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.3162393162393162,
|
1357 |
+
"grad_norm": 0.62109375,
|
1358 |
+
"learning_rate": 2.441174845423812e-05,
|
1359 |
+
"loss": 2.0688,
|
1360 |
+
"step": 185
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.31794871794871793,
|
1364 |
+
"grad_norm": 0.58984375,
|
1365 |
+
"learning_rate": 2.434869780583587e-05,
|
1366 |
+
"loss": 2.0944,
|
1367 |
+
"step": 186
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.31965811965811963,
|
1371 |
+
"grad_norm": 0.703125,
|
1372 |
+
"learning_rate": 2.4285381308809433e-05,
|
1373 |
+
"loss": 2.0466,
|
1374 |
+
"step": 187
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.3213675213675214,
|
1378 |
+
"grad_norm": 0.61328125,
|
1379 |
+
"learning_rate": 2.4221800920734716e-05,
|
1380 |
+
"loss": 2.1137,
|
1381 |
+
"step": 188
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.3230769230769231,
|
1385 |
+
"grad_norm": 0.65625,
|
1386 |
+
"learning_rate": 2.4157958607346418e-05,
|
1387 |
+
"loss": 2.1906,
|
1388 |
+
"step": 189
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.3247863247863248,
|
1392 |
+
"grad_norm": 0.69921875,
|
1393 |
+
"learning_rate": 2.409385634247727e-05,
|
1394 |
+
"loss": 2.1413,
|
1395 |
+
"step": 190
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.3264957264957265,
|
1399 |
+
"grad_norm": 0.65625,
|
1400 |
+
"learning_rate": 2.4029496107997012e-05,
|
1401 |
+
"loss": 2.108,
|
1402 |
+
"step": 191
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.3282051282051282,
|
1406 |
+
"grad_norm": 0.69140625,
|
1407 |
+
"learning_rate": 2.3964879893751098e-05,
|
1408 |
+
"loss": 2.1754,
|
1409 |
+
"step": 192
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.3299145299145299,
|
1413 |
+
"grad_norm": 0.671875,
|
1414 |
+
"learning_rate": 2.3900009697499197e-05,
|
1415 |
+
"loss": 2.4337,
|
1416 |
+
"step": 193
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.3316239316239316,
|
1420 |
+
"grad_norm": 0.93359375,
|
1421 |
+
"learning_rate": 2.383488752485341e-05,
|
1422 |
+
"loss": 2.1879,
|
1423 |
+
"step": 194
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.3333333333333333,
|
1427 |
+
"grad_norm": 0.64453125,
|
1428 |
+
"learning_rate": 2.3769515389216285e-05,
|
1429 |
+
"loss": 2.1198,
|
1430 |
+
"step": 195
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.335042735042735,
|
1434 |
+
"grad_norm": 1.1875,
|
1435 |
+
"learning_rate": 2.370389531171854e-05,
|
1436 |
+
"loss": 2.2024,
|
1437 |
+
"step": 196
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.3367521367521368,
|
1441 |
+
"grad_norm": 0.6796875,
|
1442 |
+
"learning_rate": 2.36380293211566e-05,
|
1443 |
+
"loss": 2.212,
|
1444 |
+
"step": 197
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.3384615384615385,
|
1448 |
+
"grad_norm": 0.58203125,
|
1449 |
+
"learning_rate": 2.357191945392985e-05,
|
1450 |
+
"loss": 2.0576,
|
1451 |
+
"step": 198
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.3401709401709402,
|
1455 |
+
"grad_norm": 0.65625,
|
1456 |
+
"learning_rate": 2.3505567753977698e-05,
|
1457 |
+
"loss": 2.1674,
|
1458 |
+
"step": 199
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.3418803418803419,
|
1462 |
+
"grad_norm": 0.66015625,
|
1463 |
+
"learning_rate": 2.3438976272716353e-05,
|
1464 |
+
"loss": 2.2,
|
1465 |
+
"step": 200
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.3435897435897436,
|
1469 |
+
"grad_norm": 0.640625,
|
1470 |
+
"learning_rate": 2.3372147068975443e-05,
|
1471 |
+
"loss": 2.2452,
|
1472 |
+
"step": 201
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.3452991452991453,
|
1476 |
+
"grad_norm": 0.62109375,
|
1477 |
+
"learning_rate": 2.3305082208934306e-05,
|
1478 |
+
"loss": 2.1513,
|
1479 |
+
"step": 202
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.347008547008547,
|
1483 |
+
"grad_norm": 0.66796875,
|
1484 |
+
"learning_rate": 2.323778376605816e-05,
|
1485 |
+
"loss": 2.1744,
|
1486 |
+
"step": 203
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.3487179487179487,
|
1490 |
+
"grad_norm": 0.60546875,
|
1491 |
+
"learning_rate": 2.3170253821033978e-05,
|
1492 |
+
"loss": 2.1073,
|
1493 |
+
"step": 204
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.3504273504273504,
|
1497 |
+
"grad_norm": 0.671875,
|
1498 |
+
"learning_rate": 2.3102494461706138e-05,
|
1499 |
+
"loss": 2.0887,
|
1500 |
+
"step": 205
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.35213675213675216,
|
1504 |
+
"grad_norm": 0.62109375,
|
1505 |
+
"learning_rate": 2.303450778301191e-05,
|
1506 |
+
"loss": 2.1766,
|
1507 |
+
"step": 206
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.35384615384615387,
|
1511 |
+
"grad_norm": 0.86328125,
|
1512 |
+
"learning_rate": 2.2966295886916673e-05,
|
1513 |
+
"loss": 2.4313,
|
1514 |
+
"step": 207
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.35555555555555557,
|
1518 |
+
"grad_norm": 0.640625,
|
1519 |
+
"learning_rate": 2.289786088234889e-05,
|
1520 |
+
"loss": 2.1811,
|
1521 |
+
"step": 208
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.3572649572649573,
|
1525 |
+
"grad_norm": 0.65234375,
|
1526 |
+
"learning_rate": 2.2829204885134962e-05,
|
1527 |
+
"loss": 2.1768,
|
1528 |
+
"step": 209
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.358974358974359,
|
1532 |
+
"grad_norm": 0.625,
|
1533 |
+
"learning_rate": 2.2760330017933803e-05,
|
1534 |
+
"loss": 2.1284,
|
1535 |
+
"step": 210
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.358974358974359,
|
1539 |
+
"eval_loss": 2.217427968978882,
|
1540 |
+
"eval_runtime": 87.372,
|
1541 |
+
"eval_samples_per_second": 2.93,
|
1542 |
+
"eval_steps_per_second": 0.492,
|
1543 |
+
"step": 210
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 0.3606837606837607,
|
1547 |
+
"grad_norm": 0.59765625,
|
1548 |
+
"learning_rate": 2.2691238410171176e-05,
|
1549 |
+
"loss": 2.1223,
|
1550 |
+
"step": 211
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 0.3623931623931624,
|
1554 |
+
"grad_norm": 0.62109375,
|
1555 |
+
"learning_rate": 2.2621932197973872e-05,
|
1556 |
+
"loss": 2.1968,
|
1557 |
+
"step": 212
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.3641025641025641,
|
1561 |
+
"grad_norm": 0.69921875,
|
1562 |
+
"learning_rate": 2.2552413524103696e-05,
|
1563 |
+
"loss": 2.031,
|
1564 |
+
"step": 213
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.3658119658119658,
|
1568 |
+
"grad_norm": 0.66796875,
|
1569 |
+
"learning_rate": 2.24826845378912e-05,
|
1570 |
+
"loss": 2.1201,
|
1571 |
+
"step": 214
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 0.36752136752136755,
|
1575 |
+
"grad_norm": 0.62890625,
|
1576 |
+
"learning_rate": 2.24127473951692e-05,
|
1577 |
+
"loss": 2.1512,
|
1578 |
+
"step": 215
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 0.36923076923076925,
|
1582 |
+
"grad_norm": 0.625,
|
1583 |
+
"learning_rate": 2.234260425820618e-05,
|
1584 |
+
"loss": 2.1336,
|
1585 |
+
"step": 216
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 0.37094017094017095,
|
1589 |
+
"grad_norm": 0.7109375,
|
1590 |
+
"learning_rate": 2.2272257295639394e-05,
|
1591 |
+
"loss": 2.1621,
|
1592 |
+
"step": 217
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.37264957264957266,
|
1596 |
+
"grad_norm": 0.65625,
|
1597 |
+
"learning_rate": 2.220170868240785e-05,
|
1598 |
+
"loss": 2.183,
|
1599 |
+
"step": 218
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.37435897435897436,
|
1603 |
+
"grad_norm": 0.92578125,
|
1604 |
+
"learning_rate": 2.2130960599685035e-05,
|
1605 |
+
"loss": 2.102,
|
1606 |
+
"step": 219
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 0.37606837606837606,
|
1610 |
+
"grad_norm": 0.7109375,
|
1611 |
+
"learning_rate": 2.2060015234811516e-05,
|
1612 |
+
"loss": 2.1166,
|
1613 |
+
"step": 220
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 0.37777777777777777,
|
1617 |
+
"grad_norm": 0.765625,
|
1618 |
+
"learning_rate": 2.198887478122728e-05,
|
1619 |
+
"loss": 2.0371,
|
1620 |
+
"step": 221
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 0.37948717948717947,
|
1624 |
+
"grad_norm": 0.7265625,
|
1625 |
+
"learning_rate": 2.1917541438403935e-05,
|
1626 |
+
"loss": 2.1866,
|
1627 |
+
"step": 222
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.3811965811965812,
|
1631 |
+
"grad_norm": 0.66796875,
|
1632 |
+
"learning_rate": 2.184601741177672e-05,
|
1633 |
+
"loss": 2.1378,
|
1634 |
+
"step": 223
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.38290598290598293,
|
1638 |
+
"grad_norm": 0.62109375,
|
1639 |
+
"learning_rate": 2.1774304912676283e-05,
|
1640 |
+
"loss": 2.2808,
|
1641 |
+
"step": 224
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.38461538461538464,
|
1645 |
+
"grad_norm": 0.671875,
|
1646 |
+
"learning_rate": 2.170240615826034e-05,
|
1647 |
+
"loss": 2.3453,
|
1648 |
+
"step": 225
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 0.38632478632478634,
|
1652 |
+
"grad_norm": 0.63671875,
|
1653 |
+
"learning_rate": 2.1630323371445135e-05,
|
1654 |
+
"loss": 2.0998,
|
1655 |
+
"step": 226
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 0.38803418803418804,
|
1659 |
+
"grad_norm": 0.6875,
|
1660 |
+
"learning_rate": 2.1558058780836683e-05,
|
1661 |
+
"loss": 2.1901,
|
1662 |
+
"step": 227
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 0.38974358974358975,
|
1666 |
+
"grad_norm": 0.72265625,
|
1667 |
+
"learning_rate": 2.148561462066189e-05,
|
1668 |
+
"loss": 2.1571,
|
1669 |
+
"step": 228
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 0.39145299145299145,
|
1673 |
+
"grad_norm": 0.69140625,
|
1674 |
+
"learning_rate": 2.141299313069947e-05,
|
1675 |
+
"loss": 2.1222,
|
1676 |
+
"step": 229
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 0.39316239316239315,
|
1680 |
+
"grad_norm": 0.71875,
|
1681 |
+
"learning_rate": 2.1340196556210705e-05,
|
1682 |
+
"loss": 2.0624,
|
1683 |
+
"step": 230
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.39487179487179486,
|
1687 |
+
"grad_norm": 0.6875,
|
1688 |
+
"learning_rate": 2.126722714787e-05,
|
1689 |
+
"loss": 2.1906,
|
1690 |
+
"step": 231
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 0.39658119658119656,
|
1694 |
+
"grad_norm": 1.34375,
|
1695 |
+
"learning_rate": 2.119408716169534e-05,
|
1696 |
+
"loss": 2.1405,
|
1697 |
+
"step": 232
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 0.39829059829059826,
|
1701 |
+
"grad_norm": 0.66796875,
|
1702 |
+
"learning_rate": 2.11207788589785e-05,
|
1703 |
+
"loss": 2.1191,
|
1704 |
+
"step": 233
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.4,
|
1708 |
+
"grad_norm": 0.66796875,
|
1709 |
+
"learning_rate": 2.1047304506215165e-05,
|
1710 |
+
"loss": 2.2563,
|
1711 |
+
"step": 234
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 0.4017094017094017,
|
1715 |
+
"grad_norm": 0.62890625,
|
1716 |
+
"learning_rate": 2.0973666375034834e-05,
|
1717 |
+
"loss": 2.1473,
|
1718 |
+
"step": 235
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 0.40341880341880343,
|
1722 |
+
"grad_norm": 0.64453125,
|
1723 |
+
"learning_rate": 2.0899866742130593e-05,
|
1724 |
+
"loss": 2.1922,
|
1725 |
+
"step": 236
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.40512820512820513,
|
1729 |
+
"grad_norm": 0.66015625,
|
1730 |
+
"learning_rate": 2.082590788918873e-05,
|
1731 |
+
"loss": 2.1046,
|
1732 |
+
"step": 237
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 0.40683760683760684,
|
1736 |
+
"grad_norm": 0.6484375,
|
1737 |
+
"learning_rate": 2.075179210281819e-05,
|
1738 |
+
"loss": 2.2538,
|
1739 |
+
"step": 238
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 0.40854700854700854,
|
1743 |
+
"grad_norm": 0.625,
|
1744 |
+
"learning_rate": 2.067752167447987e-05,
|
1745 |
+
"loss": 2.1669,
|
1746 |
+
"step": 239
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 0.41025641025641024,
|
1750 |
+
"grad_norm": 0.61328125,
|
1751 |
+
"learning_rate": 2.06030989004158e-05,
|
1752 |
+
"loss": 2.1102,
|
1753 |
+
"step": 240
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 0.41025641025641024,
|
1757 |
+
"eval_loss": 2.2125699520111084,
|
1758 |
+
"eval_runtime": 87.3321,
|
1759 |
+
"eval_samples_per_second": 2.931,
|
1760 |
+
"eval_steps_per_second": 0.492,
|
1761 |
+
"step": 240
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.41196581196581195,
|
1765 |
+
"grad_norm": 0.66015625,
|
1766 |
+
"learning_rate": 2.0528526081578102e-05,
|
1767 |
+
"loss": 2.1852,
|
1768 |
+
"step": 241
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 0.41367521367521365,
|
1772 |
+
"grad_norm": 0.72265625,
|
1773 |
+
"learning_rate": 2.04538055235579e-05,
|
1774 |
+
"loss": 2.1288,
|
1775 |
+
"step": 242
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 0.4153846153846154,
|
1779 |
+
"grad_norm": 0.67578125,
|
1780 |
+
"learning_rate": 2.0378939536514015e-05,
|
1781 |
+
"loss": 2.1667,
|
1782 |
+
"step": 243
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 0.4170940170940171,
|
1786 |
+
"grad_norm": 0.84765625,
|
1787 |
+
"learning_rate": 2.0303930435101532e-05,
|
1788 |
+
"loss": 2.2033,
|
1789 |
+
"step": 244
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 0.4188034188034188,
|
1793 |
+
"grad_norm": 0.625,
|
1794 |
+
"learning_rate": 2.0228780538400254e-05,
|
1795 |
+
"loss": 2.0582,
|
1796 |
+
"step": 245
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 0.4205128205128205,
|
1800 |
+
"grad_norm": 0.7109375,
|
1801 |
+
"learning_rate": 2.0153492169843002e-05,
|
1802 |
+
"loss": 2.2387,
|
1803 |
+
"step": 246
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.4222222222222222,
|
1807 |
+
"grad_norm": 0.64453125,
|
1808 |
+
"learning_rate": 2.0078067657143766e-05,
|
1809 |
+
"loss": 1.9239,
|
1810 |
+
"step": 247
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 0.4239316239316239,
|
1814 |
+
"grad_norm": 0.66015625,
|
1815 |
+
"learning_rate": 2.000250933222574e-05,
|
1816 |
+
"loss": 2.0464,
|
1817 |
+
"step": 248
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.4256410256410256,
|
1821 |
+
"grad_norm": 0.6484375,
|
1822 |
+
"learning_rate": 1.9926819531149254e-05,
|
1823 |
+
"loss": 2.3487,
|
1824 |
+
"step": 249
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.42735042735042733,
|
1828 |
+
"grad_norm": 0.671875,
|
1829 |
+
"learning_rate": 1.9851000594039507e-05,
|
1830 |
+
"loss": 2.1377,
|
1831 |
+
"step": 250
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.42905982905982903,
|
1835 |
+
"grad_norm": 0.6484375,
|
1836 |
+
"learning_rate": 1.977505486501425e-05,
|
1837 |
+
"loss": 2.1922,
|
1838 |
+
"step": 251
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 0.4307692307692308,
|
1842 |
+
"grad_norm": 0.671875,
|
1843 |
+
"learning_rate": 1.9698984692111294e-05,
|
1844 |
+
"loss": 2.2152,
|
1845 |
+
"step": 252
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.4324786324786325,
|
1849 |
+
"grad_norm": 0.6953125,
|
1850 |
+
"learning_rate": 1.9622792427215913e-05,
|
1851 |
+
"loss": 2.1691,
|
1852 |
+
"step": 253
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 0.4341880341880342,
|
1856 |
+
"grad_norm": 0.66796875,
|
1857 |
+
"learning_rate": 1.9546480425988148e-05,
|
1858 |
+
"loss": 2.0905,
|
1859 |
+
"step": 254
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 0.4358974358974359,
|
1863 |
+
"grad_norm": 0.640625,
|
1864 |
+
"learning_rate": 1.9470051047789966e-05,
|
1865 |
+
"loss": 2.1187,
|
1866 |
+
"step": 255
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 0.4376068376068376,
|
1870 |
+
"grad_norm": 0.78515625,
|
1871 |
+
"learning_rate": 1.9393506655612313e-05,
|
1872 |
+
"loss": 2.0652,
|
1873 |
+
"step": 256
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 0.4393162393162393,
|
1877 |
+
"grad_norm": 0.68359375,
|
1878 |
+
"learning_rate": 1.9316849616002043e-05,
|
1879 |
+
"loss": 2.1493,
|
1880 |
+
"step": 257
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 0.441025641025641,
|
1884 |
+
"grad_norm": 0.81640625,
|
1885 |
+
"learning_rate": 1.924008229898879e-05,
|
1886 |
+
"loss": 2.141,
|
1887 |
+
"step": 258
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.4427350427350427,
|
1891 |
+
"grad_norm": 0.6953125,
|
1892 |
+
"learning_rate": 1.916320707801166e-05,
|
1893 |
+
"loss": 2.2666,
|
1894 |
+
"step": 259
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 0.4444444444444444,
|
1898 |
+
"grad_norm": 0.70703125,
|
1899 |
+
"learning_rate": 1.908622632984584e-05,
|
1900 |
+
"loss": 2.1914,
|
1901 |
+
"step": 260
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 0.4461538461538462,
|
1905 |
+
"grad_norm": 0.734375,
|
1906 |
+
"learning_rate": 1.9009142434529165e-05,
|
1907 |
+
"loss": 2.0921,
|
1908 |
+
"step": 261
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 0.4478632478632479,
|
1912 |
+
"grad_norm": 0.72265625,
|
1913 |
+
"learning_rate": 1.8931957775288488e-05,
|
1914 |
+
"loss": 2.2453,
|
1915 |
+
"step": 262
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 0.4495726495726496,
|
1919 |
+
"grad_norm": 0.703125,
|
1920 |
+
"learning_rate": 1.8854674738466007e-05,
|
1921 |
+
"loss": 2.2583,
|
1922 |
+
"step": 263
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 0.4512820512820513,
|
1926 |
+
"grad_norm": 0.62890625,
|
1927 |
+
"learning_rate": 1.8777295713445494e-05,
|
1928 |
+
"loss": 2.2228,
|
1929 |
+
"step": 264
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.452991452991453,
|
1933 |
+
"grad_norm": 0.69921875,
|
1934 |
+
"learning_rate": 1.8699823092578427e-05,
|
1935 |
+
"loss": 2.1037,
|
1936 |
+
"step": 265
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 0.4547008547008547,
|
1940 |
+
"grad_norm": 1.375,
|
1941 |
+
"learning_rate": 1.862225927111001e-05,
|
1942 |
+
"loss": 2.3323,
|
1943 |
+
"step": 266
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 0.4564102564102564,
|
1947 |
+
"grad_norm": 0.68359375,
|
1948 |
+
"learning_rate": 1.8544606647105113e-05,
|
1949 |
+
"loss": 2.1672,
|
1950 |
+
"step": 267
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 0.4581196581196581,
|
1954 |
+
"grad_norm": 0.70703125,
|
1955 |
+
"learning_rate": 1.8466867621374162e-05,
|
1956 |
+
"loss": 2.0741,
|
1957 |
+
"step": 268
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 0.4598290598290598,
|
1961 |
+
"grad_norm": 0.66796875,
|
1962 |
+
"learning_rate": 1.8389044597398877e-05,
|
1963 |
+
"loss": 2.153,
|
1964 |
+
"step": 269
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 0.46153846153846156,
|
1968 |
+
"grad_norm": 0.69921875,
|
1969 |
+
"learning_rate": 1.831113998125798e-05,
|
1970 |
+
"loss": 2.146,
|
1971 |
+
"step": 270
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.46153846153846156,
|
1975 |
+
"eval_loss": 2.21103835105896,
|
1976 |
+
"eval_runtime": 87.3912,
|
1977 |
+
"eval_samples_per_second": 2.929,
|
1978 |
+
"eval_steps_per_second": 0.492,
|
1979 |
+
"step": 270
|
1980 |
+
},
|
1981 |
+
{
|
1982 |
+
"epoch": 0.46324786324786327,
|
1983 |
+
"grad_norm": 0.8125,
|
1984 |
+
"learning_rate": 1.8233156181552815e-05,
|
1985 |
+
"loss": 2.23,
|
1986 |
+
"step": 271
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 0.46495726495726497,
|
1990 |
+
"grad_norm": 0.6484375,
|
1991 |
+
"learning_rate": 1.8155095609332857e-05,
|
1992 |
+
"loss": 2.1312,
|
1993 |
+
"step": 272
|
1994 |
+
},
|
1995 |
+
{
|
1996 |
+
"epoch": 0.4666666666666667,
|
1997 |
+
"grad_norm": 0.6328125,
|
1998 |
+
"learning_rate": 1.807696067802118e-05,
|
1999 |
+
"loss": 2.2045,
|
2000 |
+
"step": 273
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 0.4683760683760684,
|
2004 |
+
"grad_norm": 0.72265625,
|
2005 |
+
"learning_rate": 1.7998753803339846e-05,
|
2006 |
+
"loss": 2.1149,
|
2007 |
+
"step": 274
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 0.4700854700854701,
|
2011 |
+
"grad_norm": 0.8359375,
|
2012 |
+
"learning_rate": 1.792047740323522e-05,
|
2013 |
+
"loss": 2.1843,
|
2014 |
+
"step": 275
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"epoch": 0.4717948717948718,
|
2018 |
+
"grad_norm": 0.6796875,
|
2019 |
+
"learning_rate": 1.7842133897803194e-05,
|
2020 |
+
"loss": 2.0823,
|
2021 |
+
"step": 276
|
2022 |
+
},
|
2023 |
+
{
|
2024 |
+
"epoch": 0.4735042735042735,
|
2025 |
+
"grad_norm": 0.79296875,
|
2026 |
+
"learning_rate": 1.776372570921438e-05,
|
2027 |
+
"loss": 2.133,
|
2028 |
+
"step": 277
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 0.4752136752136752,
|
2032 |
+
"grad_norm": 0.62109375,
|
2033 |
+
"learning_rate": 1.7685255261639223e-05,
|
2034 |
+
"loss": 2.0865,
|
2035 |
+
"step": 278
|
2036 |
+
},
|
2037 |
+
{
|
2038 |
+
"epoch": 0.47692307692307695,
|
2039 |
+
"grad_norm": 4.28125,
|
2040 |
+
"learning_rate": 1.760672498117304e-05,
|
2041 |
+
"loss": 2.1211,
|
2042 |
+
"step": 279
|
2043 |
+
},
|
2044 |
+
{
|
2045 |
+
"epoch": 0.47863247863247865,
|
2046 |
+
"grad_norm": 0.640625,
|
2047 |
+
"learning_rate": 1.7528137295761025e-05,
|
2048 |
+
"loss": 2.1688,
|
2049 |
+
"step": 280
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 0.48034188034188036,
|
2053 |
+
"grad_norm": 0.71484375,
|
2054 |
+
"learning_rate": 1.7449494635123183e-05,
|
2055 |
+
"loss": 2.1924,
|
2056 |
+
"step": 281
|
2057 |
+
},
|
2058 |
+
{
|
2059 |
+
"epoch": 0.48205128205128206,
|
2060 |
+
"grad_norm": 0.68359375,
|
2061 |
+
"learning_rate": 1.737079943067921e-05,
|
2062 |
+
"loss": 2.214,
|
2063 |
+
"step": 282
|
2064 |
+
},
|
2065 |
+
{
|
2066 |
+
"epoch": 0.48376068376068376,
|
2067 |
+
"grad_norm": 0.74609375,
|
2068 |
+
"learning_rate": 1.7292054115473292e-05,
|
2069 |
+
"loss": 2.1239,
|
2070 |
+
"step": 283
|
2071 |
+
},
|
2072 |
+
{
|
2073 |
+
"epoch": 0.48547008547008547,
|
2074 |
+
"grad_norm": 0.6953125,
|
2075 |
+
"learning_rate": 1.7213261124098926e-05,
|
2076 |
+
"loss": 1.9381,
|
2077 |
+
"step": 284
|
2078 |
+
},
|
2079 |
+
{
|
2080 |
+
"epoch": 0.48717948717948717,
|
2081 |
+
"grad_norm": 0.76171875,
|
2082 |
+
"learning_rate": 1.7134422892623625e-05,
|
2083 |
+
"loss": 2.0799,
|
2084 |
+
"step": 285
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 0.4888888888888889,
|
2088 |
+
"grad_norm": 0.7421875,
|
2089 |
+
"learning_rate": 1.70555418585136e-05,
|
2090 |
+
"loss": 2.0629,
|
2091 |
+
"step": 286
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 0.4905982905982906,
|
2095 |
+
"grad_norm": 0.66796875,
|
2096 |
+
"learning_rate": 1.69766204605584e-05,
|
2097 |
+
"loss": 2.0974,
|
2098 |
+
"step": 287
|
2099 |
+
},
|
2100 |
+
{
|
2101 |
+
"epoch": 0.49230769230769234,
|
2102 |
+
"grad_norm": 1.15625,
|
2103 |
+
"learning_rate": 1.689766113879553e-05,
|
2104 |
+
"loss": 2.0869,
|
2105 |
+
"step": 288
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 0.49401709401709404,
|
2109 |
+
"grad_norm": 0.734375,
|
2110 |
+
"learning_rate": 1.6818666334434983e-05,
|
2111 |
+
"loss": 2.037,
|
2112 |
+
"step": 289
|
2113 |
+
},
|
2114 |
+
{
|
2115 |
+
"epoch": 0.49572649572649574,
|
2116 |
+
"grad_norm": 0.8203125,
|
2117 |
+
"learning_rate": 1.673963848978378e-05,
|
2118 |
+
"loss": 2.1412,
|
2119 |
+
"step": 290
|
2120 |
+
},
|
2121 |
+
{
|
2122 |
+
"epoch": 0.49743589743589745,
|
2123 |
+
"grad_norm": 0.734375,
|
2124 |
+
"learning_rate": 1.6660580048170472e-05,
|
2125 |
+
"loss": 2.1773,
|
2126 |
+
"step": 291
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 0.49914529914529915,
|
2130 |
+
"grad_norm": 1.078125,
|
2131 |
+
"learning_rate": 1.6581493453869575e-05,
|
2132 |
+
"loss": 2.1232,
|
2133 |
+
"step": 292
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 0.5008547008547009,
|
2137 |
+
"grad_norm": 0.65234375,
|
2138 |
+
"learning_rate": 1.6502381152026006e-05,
|
2139 |
+
"loss": 2.1975,
|
2140 |
+
"step": 293
|
2141 |
+
}
|
2142 |
+
],
|
2143 |
+
"logging_steps": 1,
|
2144 |
+
"max_steps": 585,
|
2145 |
+
"num_input_tokens_seen": 0,
|
2146 |
+
"num_train_epochs": 1,
|
2147 |
+
"save_steps": 293,
|
2148 |
+
"stateful_callbacks": {
|
2149 |
+
"TrainerControl": {
|
2150 |
+
"args": {
|
2151 |
+
"should_epoch_stop": false,
|
2152 |
+
"should_evaluate": false,
|
2153 |
+
"should_log": false,
|
2154 |
+
"should_save": true,
|
2155 |
+
"should_training_stop": false
|
2156 |
+
},
|
2157 |
+
"attributes": {}
|
2158 |
+
}
|
2159 |
+
},
|
2160 |
+
"total_flos": 2.5500999342882816e+17,
|
2161 |
+
"train_batch_size": 6,
|
2162 |
+
"trial_name": null,
|
2163 |
+
"trial_params": null
|
2164 |
+
}
|
checkpoint-293/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c92115980639817e5ee97c88f36ed2c459a54b1a3843b6bd74d0e1691e25fd50
|
3 |
+
size 6136
|