Training in progress, step 300, checkpoint
Browse files- checkpoint-300/README.md +202 -0
- checkpoint-300/adapter_config.json +34 -0
- checkpoint-300/adapter_model.safetensors +3 -0
- checkpoint-300/added_tokens.json +17 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state_0.pth +3 -0
- checkpoint-300/rng_state_1.pth +3 -0
- checkpoint-300/rng_state_2.pth +3 -0
- checkpoint-300/rng_state_3.pth +3 -0
- checkpoint-300/rng_state_4.pth +3 -0
- checkpoint-300/rng_state_5.pth +3 -0
- checkpoint-300/rng_state_6.pth +3 -0
- checkpoint-300/rng_state_7.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +30 -0
- checkpoint-300/tokenizer.json +0 -0
- checkpoint-300/tokenizer.model +3 -0
- checkpoint-300/tokenizer_config.json +163 -0
- checkpoint-300/trainer_state.json +2197 -0
- checkpoint-300/training_args.bin +3 -0
checkpoint-300/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
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-300/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
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": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 512,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"gate_up_proj",
|
27 |
+
"down_proj",
|
28 |
+
"o_proj",
|
29 |
+
"qkv_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-300/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60fe5b70e59b2ebeddd28513fd39db4c9dd3f8684a55e79f15cee84c51d3550d
|
3 |
+
size 2004651224
|
checkpoint-300/added_tokens.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</plan>": 32014,
|
3 |
+
"</thinking>": 32012,
|
4 |
+
"<plan>": 32013,
|
5 |
+
"<thinking>": 32011,
|
6 |
+
"<|assistant|>": 32001,
|
7 |
+
"<|endoftext|>": 32000,
|
8 |
+
"<|end|>": 32007,
|
9 |
+
"<|placeholder1|>": 32002,
|
10 |
+
"<|placeholder2|>": 32003,
|
11 |
+
"<|placeholder3|>": 32004,
|
12 |
+
"<|placeholder4|>": 32005,
|
13 |
+
"<|placeholder5|>": 32008,
|
14 |
+
"<|placeholder6|>": 32009,
|
15 |
+
"<|system|>": 32006,
|
16 |
+
"<|user|>": 32010
|
17 |
+
}
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:894488035437f587cb88fea0b7eba04bc6a08c254727c27c29a22613adba02a9
|
3 |
+
size 4009448634
|
checkpoint-300/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:155980f8ca2dac19c15298068a5d564e9fd9c2a6bd699727a9b4b40f7225aea8
|
3 |
+
size 15984
|
checkpoint-300/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30ea79ff98d65e758d55a9c807a84b989e6778620c1defa590dfb3b94c528f89
|
3 |
+
size 15984
|
checkpoint-300/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7c6a62653ba5ce15530de6cbcf4a3f2987c8606143149a33ce36863ec226ad2
|
3 |
+
size 15984
|
checkpoint-300/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68635ed424947443fbd736471d033e55ff35e7ef9d6845d0e0cfc6812e5ac0b1
|
3 |
+
size 15984
|
checkpoint-300/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1d77e8c21d7b489ba8ca2962081f4b8843db515a5e66e029424ee3ea8dd7f45
|
3 |
+
size 15984
|
checkpoint-300/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:814d24d9c622cfa0d389d4cb35079aacc55b1a54c781ee1d7730330960b9e04e
|
3 |
+
size 15984
|
checkpoint-300/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9726aa6d0c3640facdba38f39cdcb21ae0c854e68b6529717aef135454833fa
|
3 |
+
size 15984
|
checkpoint-300/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c201a8194443543b2d67b8fd0c6bdbc2c200e0265d8f356ec3cf94990d559e06
|
3 |
+
size 15984
|
checkpoint-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28e93e4164c993edc6e80f3fcad5deeb8514474dbaa92febf17d6d06c029a04e
|
3 |
+
size 1064
|
checkpoint-300/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": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
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-300/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-300/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-300/tokenizer_config.json
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<thinking>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "</thinking>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<plan>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "</plan>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
}
|
150 |
+
},
|
151 |
+
"bos_token": "<s>",
|
152 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
153 |
+
"clean_up_tokenization_spaces": false,
|
154 |
+
"eos_token": "<|endoftext|>",
|
155 |
+
"legacy": false,
|
156 |
+
"model_max_length": 4096,
|
157 |
+
"pad_token": "<|endoftext|>",
|
158 |
+
"padding_side": "left",
|
159 |
+
"sp_model_kwargs": {},
|
160 |
+
"tokenizer_class": "LlamaTokenizer",
|
161 |
+
"unk_token": "<unk>",
|
162 |
+
"use_default_system_prompt": false
|
163 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
@@ -0,0 +1,2197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0101010101010102,
|
5 |
+
"eval_steps": 38,
|
6 |
+
"global_step": 300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.003367003367003367,
|
13 |
+
"grad_norm": 2.0,
|
14 |
+
"learning_rate": 2.2727272727272729e-07,
|
15 |
+
"loss": 1.0833,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.003367003367003367,
|
20 |
+
"eval_loss": 1.032954454421997,
|
21 |
+
"eval_runtime": 8.7985,
|
22 |
+
"eval_samples_per_second": 56.828,
|
23 |
+
"eval_steps_per_second": 3.637,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.006734006734006734,
|
28 |
+
"grad_norm": 2.265625,
|
29 |
+
"learning_rate": 4.5454545454545457e-07,
|
30 |
+
"loss": 0.996,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.010101010101010102,
|
35 |
+
"grad_norm": 1.640625,
|
36 |
+
"learning_rate": 6.818181818181818e-07,
|
37 |
+
"loss": 1.0489,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.013468013468013467,
|
42 |
+
"grad_norm": 2.0625,
|
43 |
+
"learning_rate": 9.090909090909091e-07,
|
44 |
+
"loss": 1.0546,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.016835016835016835,
|
49 |
+
"grad_norm": 2.453125,
|
50 |
+
"learning_rate": 1.1363636363636364e-06,
|
51 |
+
"loss": 1.0341,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.020202020202020204,
|
56 |
+
"grad_norm": 1.9921875,
|
57 |
+
"learning_rate": 1.3636363636363636e-06,
|
58 |
+
"loss": 1.0136,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.02356902356902357,
|
63 |
+
"grad_norm": 2.640625,
|
64 |
+
"learning_rate": 1.590909090909091e-06,
|
65 |
+
"loss": 1.0305,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.026936026936026935,
|
70 |
+
"grad_norm": 2.359375,
|
71 |
+
"learning_rate": 1.8181818181818183e-06,
|
72 |
+
"loss": 1.0226,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.030303030303030304,
|
77 |
+
"grad_norm": 2.3125,
|
78 |
+
"learning_rate": 2.0454545454545457e-06,
|
79 |
+
"loss": 1.0745,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.03367003367003367,
|
84 |
+
"grad_norm": 2.359375,
|
85 |
+
"learning_rate": 2.2727272727272728e-06,
|
86 |
+
"loss": 1.0232,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.037037037037037035,
|
91 |
+
"grad_norm": 2.53125,
|
92 |
+
"learning_rate": 2.5e-06,
|
93 |
+
"loss": 1.0106,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.04040404040404041,
|
98 |
+
"grad_norm": 2.125,
|
99 |
+
"learning_rate": 2.7272727272727272e-06,
|
100 |
+
"loss": 1.0541,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.04377104377104377,
|
105 |
+
"grad_norm": 2.15625,
|
106 |
+
"learning_rate": 2.954545454545455e-06,
|
107 |
+
"loss": 1.0693,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.04713804713804714,
|
112 |
+
"grad_norm": 1.8359375,
|
113 |
+
"learning_rate": 3.181818181818182e-06,
|
114 |
+
"loss": 1.0338,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.050505050505050504,
|
119 |
+
"grad_norm": 2.0,
|
120 |
+
"learning_rate": 3.409090909090909e-06,
|
121 |
+
"loss": 1.0464,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.05387205387205387,
|
126 |
+
"grad_norm": 2.34375,
|
127 |
+
"learning_rate": 3.6363636363636366e-06,
|
128 |
+
"loss": 1.0684,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05723905723905724,
|
133 |
+
"grad_norm": 1.8125,
|
134 |
+
"learning_rate": 3.863636363636364e-06,
|
135 |
+
"loss": 1.0117,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.06060606060606061,
|
140 |
+
"grad_norm": 1.90625,
|
141 |
+
"learning_rate": 4.0909090909090915e-06,
|
142 |
+
"loss": 1.0138,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.06397306397306397,
|
147 |
+
"grad_norm": 1.59375,
|
148 |
+
"learning_rate": 4.3181818181818185e-06,
|
149 |
+
"loss": 0.9873,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.06734006734006734,
|
154 |
+
"grad_norm": 1.59375,
|
155 |
+
"learning_rate": 4.5454545454545455e-06,
|
156 |
+
"loss": 1.0524,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.0707070707070707,
|
161 |
+
"grad_norm": 1.3984375,
|
162 |
+
"learning_rate": 4.772727272727273e-06,
|
163 |
+
"loss": 1.0479,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.07407407407407407,
|
168 |
+
"grad_norm": 1.609375,
|
169 |
+
"learning_rate": 5e-06,
|
170 |
+
"loss": 0.9894,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07744107744107744,
|
175 |
+
"grad_norm": 1.3671875,
|
176 |
+
"learning_rate": 5.2272727272727274e-06,
|
177 |
+
"loss": 0.983,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.08080808080808081,
|
182 |
+
"grad_norm": 1.6328125,
|
183 |
+
"learning_rate": 5.4545454545454545e-06,
|
184 |
+
"loss": 1.0563,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.08417508417508418,
|
189 |
+
"grad_norm": 1.34375,
|
190 |
+
"learning_rate": 5.681818181818183e-06,
|
191 |
+
"loss": 0.9966,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.08754208754208755,
|
196 |
+
"grad_norm": 1.25,
|
197 |
+
"learning_rate": 5.90909090909091e-06,
|
198 |
+
"loss": 0.9922,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.09090909090909091,
|
203 |
+
"grad_norm": 1.3984375,
|
204 |
+
"learning_rate": 6.136363636363637e-06,
|
205 |
+
"loss": 1.0677,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.09427609427609428,
|
210 |
+
"grad_norm": 1.3828125,
|
211 |
+
"learning_rate": 6.363636363636364e-06,
|
212 |
+
"loss": 1.0325,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09764309764309764,
|
217 |
+
"grad_norm": 1.1953125,
|
218 |
+
"learning_rate": 6.590909090909091e-06,
|
219 |
+
"loss": 1.0159,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.10101010101010101,
|
224 |
+
"grad_norm": 1.3125,
|
225 |
+
"learning_rate": 6.818181818181818e-06,
|
226 |
+
"loss": 1.0384,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.10437710437710437,
|
231 |
+
"grad_norm": 1.1171875,
|
232 |
+
"learning_rate": 7.045454545454546e-06,
|
233 |
+
"loss": 0.9949,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.10774410774410774,
|
238 |
+
"grad_norm": 1.2421875,
|
239 |
+
"learning_rate": 7.272727272727273e-06,
|
240 |
+
"loss": 1.0284,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.1111111111111111,
|
245 |
+
"grad_norm": 1.15625,
|
246 |
+
"learning_rate": 7.500000000000001e-06,
|
247 |
+
"loss": 1.0245,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11447811447811448,
|
252 |
+
"grad_norm": 1.1875,
|
253 |
+
"learning_rate": 7.727272727272727e-06,
|
254 |
+
"loss": 1.0103,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11784511784511785,
|
259 |
+
"grad_norm": 1.125,
|
260 |
+
"learning_rate": 7.954545454545455e-06,
|
261 |
+
"loss": 1.0129,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.12121212121212122,
|
266 |
+
"grad_norm": 1.03125,
|
267 |
+
"learning_rate": 8.181818181818183e-06,
|
268 |
+
"loss": 0.965,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.12457912457912458,
|
273 |
+
"grad_norm": 1.109375,
|
274 |
+
"learning_rate": 8.40909090909091e-06,
|
275 |
+
"loss": 1.0027,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.12794612794612795,
|
280 |
+
"grad_norm": 1.0859375,
|
281 |
+
"learning_rate": 8.636363636363637e-06,
|
282 |
+
"loss": 1.0093,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.12794612794612795,
|
287 |
+
"eval_loss": 0.9909602999687195,
|
288 |
+
"eval_runtime": 8.9064,
|
289 |
+
"eval_samples_per_second": 56.139,
|
290 |
+
"eval_steps_per_second": 3.593,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.13131313131313133,
|
295 |
+
"grad_norm": 0.96484375,
|
296 |
+
"learning_rate": 8.863636363636365e-06,
|
297 |
+
"loss": 0.98,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.13468013468013468,
|
302 |
+
"grad_norm": 1.0078125,
|
303 |
+
"learning_rate": 9.090909090909091e-06,
|
304 |
+
"loss": 1.0,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.13804713804713806,
|
309 |
+
"grad_norm": 1.109375,
|
310 |
+
"learning_rate": 9.318181818181819e-06,
|
311 |
+
"loss": 0.9658,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.1414141414141414,
|
316 |
+
"grad_norm": 0.95703125,
|
317 |
+
"learning_rate": 9.545454545454547e-06,
|
318 |
+
"loss": 0.9656,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.1447811447811448,
|
323 |
+
"grad_norm": 1.0,
|
324 |
+
"learning_rate": 9.772727272727273e-06,
|
325 |
+
"loss": 0.9528,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.14814814814814814,
|
330 |
+
"grad_norm": 0.88671875,
|
331 |
+
"learning_rate": 1e-05,
|
332 |
+
"loss": 0.9546,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.15151515151515152,
|
337 |
+
"grad_norm": 0.984375,
|
338 |
+
"learning_rate": 9.999965606811854e-06,
|
339 |
+
"loss": 0.9406,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.15488215488215487,
|
344 |
+
"grad_norm": 1.0625,
|
345 |
+
"learning_rate": 9.99986242772057e-06,
|
346 |
+
"loss": 0.9975,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.15824915824915825,
|
351 |
+
"grad_norm": 0.94140625,
|
352 |
+
"learning_rate": 9.99969046414561e-06,
|
353 |
+
"loss": 0.9567,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.16161616161616163,
|
358 |
+
"grad_norm": 0.96484375,
|
359 |
+
"learning_rate": 9.999449718452724e-06,
|
360 |
+
"loss": 0.9707,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.16498316498316498,
|
365 |
+
"grad_norm": 1.0,
|
366 |
+
"learning_rate": 9.999140193953923e-06,
|
367 |
+
"loss": 0.9559,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.16835016835016836,
|
372 |
+
"grad_norm": 0.99609375,
|
373 |
+
"learning_rate": 9.998761894907414e-06,
|
374 |
+
"loss": 0.9398,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.1717171717171717,
|
379 |
+
"grad_norm": 0.83203125,
|
380 |
+
"learning_rate": 9.998314826517564e-06,
|
381 |
+
"loss": 0.9329,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.1750841750841751,
|
386 |
+
"grad_norm": 0.91015625,
|
387 |
+
"learning_rate": 9.997798994934812e-06,
|
388 |
+
"loss": 0.9478,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.17845117845117844,
|
393 |
+
"grad_norm": 0.94140625,
|
394 |
+
"learning_rate": 9.997214407255602e-06,
|
395 |
+
"loss": 0.9062,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.18181818181818182,
|
400 |
+
"grad_norm": 0.83203125,
|
401 |
+
"learning_rate": 9.996561071522264e-06,
|
402 |
+
"loss": 0.9089,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.18518518518518517,
|
407 |
+
"grad_norm": 1.0078125,
|
408 |
+
"learning_rate": 9.995838996722916e-06,
|
409 |
+
"loss": 0.9561,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.18855218855218855,
|
414 |
+
"grad_norm": 0.796875,
|
415 |
+
"learning_rate": 9.995048192791341e-06,
|
416 |
+
"loss": 0.8948,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.1919191919191919,
|
421 |
+
"grad_norm": 0.91796875,
|
422 |
+
"learning_rate": 9.994188670606845e-06,
|
423 |
+
"loss": 0.9095,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.19528619528619529,
|
428 |
+
"grad_norm": 0.8515625,
|
429 |
+
"learning_rate": 9.993260441994116e-06,
|
430 |
+
"loss": 0.9137,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.19865319865319866,
|
435 |
+
"grad_norm": 0.8671875,
|
436 |
+
"learning_rate": 9.992263519723046e-06,
|
437 |
+
"loss": 0.9012,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.20202020202020202,
|
442 |
+
"grad_norm": 0.8046875,
|
443 |
+
"learning_rate": 9.99119791750857e-06,
|
444 |
+
"loss": 0.9074,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.2053872053872054,
|
449 |
+
"grad_norm": 1.0859375,
|
450 |
+
"learning_rate": 9.990063650010473e-06,
|
451 |
+
"loss": 0.9106,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.20875420875420875,
|
456 |
+
"grad_norm": 1.0625,
|
457 |
+
"learning_rate": 9.988860732833183e-06,
|
458 |
+
"loss": 0.9012,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.21212121212121213,
|
463 |
+
"grad_norm": 0.93359375,
|
464 |
+
"learning_rate": 9.987589182525562e-06,
|
465 |
+
"loss": 0.8928,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.21548821548821548,
|
470 |
+
"grad_norm": 0.921875,
|
471 |
+
"learning_rate": 9.98624901658068e-06,
|
472 |
+
"loss": 0.9487,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.21885521885521886,
|
477 |
+
"grad_norm": 0.92578125,
|
478 |
+
"learning_rate": 9.984840253435569e-06,
|
479 |
+
"loss": 0.8887,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.2222222222222222,
|
484 |
+
"grad_norm": 0.8671875,
|
485 |
+
"learning_rate": 9.983362912470967e-06,
|
486 |
+
"loss": 0.9152,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.2255892255892256,
|
491 |
+
"grad_norm": 0.83984375,
|
492 |
+
"learning_rate": 9.981817014011066e-06,
|
493 |
+
"loss": 0.8849,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.22895622895622897,
|
498 |
+
"grad_norm": 0.94921875,
|
499 |
+
"learning_rate": 9.980202579323212e-06,
|
500 |
+
"loss": 0.9386,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.23232323232323232,
|
505 |
+
"grad_norm": 0.8203125,
|
506 |
+
"learning_rate": 9.978519630617632e-06,
|
507 |
+
"loss": 0.8651,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.2356902356902357,
|
512 |
+
"grad_norm": 0.7109375,
|
513 |
+
"learning_rate": 9.976768191047109e-06,
|
514 |
+
"loss": 0.9044,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.23905723905723905,
|
519 |
+
"grad_norm": 1.03125,
|
520 |
+
"learning_rate": 9.974948284706684e-06,
|
521 |
+
"loss": 0.8702,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.24242424242424243,
|
526 |
+
"grad_norm": 0.91796875,
|
527 |
+
"learning_rate": 9.973059936633308e-06,
|
528 |
+
"loss": 0.8748,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.24579124579124578,
|
533 |
+
"grad_norm": 0.66796875,
|
534 |
+
"learning_rate": 9.971103172805504e-06,
|
535 |
+
"loss": 0.8443,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.24915824915824916,
|
540 |
+
"grad_norm": 0.671875,
|
541 |
+
"learning_rate": 9.969078020143013e-06,
|
542 |
+
"loss": 0.8605,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.25252525252525254,
|
547 |
+
"grad_norm": 0.6796875,
|
548 |
+
"learning_rate": 9.966984506506415e-06,
|
549 |
+
"loss": 0.8661,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.2558922558922559,
|
554 |
+
"grad_norm": 0.953125,
|
555 |
+
"learning_rate": 9.964822660696753e-06,
|
556 |
+
"loss": 0.9169,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2558922558922559,
|
561 |
+
"eval_loss": 0.8667835593223572,
|
562 |
+
"eval_runtime": 8.6819,
|
563 |
+
"eval_samples_per_second": 57.591,
|
564 |
+
"eval_steps_per_second": 3.686,
|
565 |
+
"step": 76
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.25925925925925924,
|
569 |
+
"grad_norm": 0.86328125,
|
570 |
+
"learning_rate": 9.96259251245514e-06,
|
571 |
+
"loss": 0.8719,
|
572 |
+
"step": 77
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.26262626262626265,
|
576 |
+
"grad_norm": 0.66796875,
|
577 |
+
"learning_rate": 9.960294092462332e-06,
|
578 |
+
"loss": 0.8438,
|
579 |
+
"step": 78
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.265993265993266,
|
583 |
+
"grad_norm": 0.66796875,
|
584 |
+
"learning_rate": 9.957927432338332e-06,
|
585 |
+
"loss": 0.8723,
|
586 |
+
"step": 79
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.26936026936026936,
|
590 |
+
"grad_norm": 1.3828125,
|
591 |
+
"learning_rate": 9.95549256464193e-06,
|
592 |
+
"loss": 0.8987,
|
593 |
+
"step": 80
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.2727272727272727,
|
597 |
+
"grad_norm": 0.69921875,
|
598 |
+
"learning_rate": 9.952989522870275e-06,
|
599 |
+
"loss": 0.8188,
|
600 |
+
"step": 81
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.2760942760942761,
|
604 |
+
"grad_norm": 0.9375,
|
605 |
+
"learning_rate": 9.950418341458398e-06,
|
606 |
+
"loss": 0.8521,
|
607 |
+
"step": 82
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 0.27946127946127947,
|
611 |
+
"grad_norm": 0.828125,
|
612 |
+
"learning_rate": 9.947779055778752e-06,
|
613 |
+
"loss": 0.8305,
|
614 |
+
"step": 83
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.2828282828282828,
|
618 |
+
"grad_norm": 0.9453125,
|
619 |
+
"learning_rate": 9.945071702140716e-06,
|
620 |
+
"loss": 0.856,
|
621 |
+
"step": 84
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.28619528619528617,
|
625 |
+
"grad_norm": 0.609375,
|
626 |
+
"learning_rate": 9.9422963177901e-06,
|
627 |
+
"loss": 0.8512,
|
628 |
+
"step": 85
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.2895622895622896,
|
632 |
+
"grad_norm": 1.546875,
|
633 |
+
"learning_rate": 9.939452940908627e-06,
|
634 |
+
"loss": 0.818,
|
635 |
+
"step": 86
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.29292929292929293,
|
639 |
+
"grad_norm": 0.640625,
|
640 |
+
"learning_rate": 9.936541610613417e-06,
|
641 |
+
"loss": 0.8071,
|
642 |
+
"step": 87
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.2962962962962963,
|
646 |
+
"grad_norm": 0.82421875,
|
647 |
+
"learning_rate": 9.933562366956445e-06,
|
648 |
+
"loss": 0.8559,
|
649 |
+
"step": 88
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.2996632996632997,
|
653 |
+
"grad_norm": 1.046875,
|
654 |
+
"learning_rate": 9.930515250923985e-06,
|
655 |
+
"loss": 0.8646,
|
656 |
+
"step": 89
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.30303030303030304,
|
660 |
+
"grad_norm": 0.76953125,
|
661 |
+
"learning_rate": 9.927400304436048e-06,
|
662 |
+
"loss": 0.8179,
|
663 |
+
"step": 90
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.3063973063973064,
|
667 |
+
"grad_norm": 1.09375,
|
668 |
+
"learning_rate": 9.924217570345814e-06,
|
669 |
+
"loss": 0.8093,
|
670 |
+
"step": 91
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 0.30976430976430974,
|
674 |
+
"grad_norm": 0.6015625,
|
675 |
+
"learning_rate": 9.920967092439028e-06,
|
676 |
+
"loss": 0.8073,
|
677 |
+
"step": 92
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.31313131313131315,
|
681 |
+
"grad_norm": 0.84375,
|
682 |
+
"learning_rate": 9.917648915433413e-06,
|
683 |
+
"loss": 0.9031,
|
684 |
+
"step": 93
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3164983164983165,
|
688 |
+
"grad_norm": 0.76171875,
|
689 |
+
"learning_rate": 9.914263084978041e-06,
|
690 |
+
"loss": 0.8568,
|
691 |
+
"step": 94
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.31986531986531985,
|
695 |
+
"grad_norm": 0.8671875,
|
696 |
+
"learning_rate": 9.910809647652716e-06,
|
697 |
+
"loss": 0.7819,
|
698 |
+
"step": 95
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.32323232323232326,
|
702 |
+
"grad_norm": 0.84765625,
|
703 |
+
"learning_rate": 9.907288650967324e-06,
|
704 |
+
"loss": 0.8236,
|
705 |
+
"step": 96
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.3265993265993266,
|
709 |
+
"grad_norm": 0.70703125,
|
710 |
+
"learning_rate": 9.903700143361185e-06,
|
711 |
+
"loss": 0.8418,
|
712 |
+
"step": 97
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 0.32996632996632996,
|
716 |
+
"grad_norm": 0.94921875,
|
717 |
+
"learning_rate": 9.900044174202389e-06,
|
718 |
+
"loss": 0.8313,
|
719 |
+
"step": 98
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.3333333333333333,
|
723 |
+
"grad_norm": 0.8125,
|
724 |
+
"learning_rate": 9.896320793787106e-06,
|
725 |
+
"loss": 0.8158,
|
726 |
+
"step": 99
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.3367003367003367,
|
730 |
+
"grad_norm": 0.76171875,
|
731 |
+
"learning_rate": 9.892530053338909e-06,
|
732 |
+
"loss": 0.7956,
|
733 |
+
"step": 100
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.3400673400673401,
|
737 |
+
"grad_norm": 0.94921875,
|
738 |
+
"learning_rate": 9.888672005008054e-06,
|
739 |
+
"loss": 0.8154,
|
740 |
+
"step": 101
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.3434343434343434,
|
744 |
+
"grad_norm": 0.6328125,
|
745 |
+
"learning_rate": 9.884746701870778e-06,
|
746 |
+
"loss": 0.8322,
|
747 |
+
"step": 102
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.3468013468013468,
|
751 |
+
"grad_norm": 0.62890625,
|
752 |
+
"learning_rate": 9.880754197928553e-06,
|
753 |
+
"loss": 0.8133,
|
754 |
+
"step": 103
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.3501683501683502,
|
758 |
+
"grad_norm": 0.76953125,
|
759 |
+
"learning_rate": 9.876694548107358e-06,
|
760 |
+
"loss": 0.7882,
|
761 |
+
"step": 104
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.35353535353535354,
|
765 |
+
"grad_norm": 1.03125,
|
766 |
+
"learning_rate": 9.87256780825691e-06,
|
767 |
+
"loss": 0.8264,
|
768 |
+
"step": 105
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.3569023569023569,
|
772 |
+
"grad_norm": 0.7421875,
|
773 |
+
"learning_rate": 9.868374035149906e-06,
|
774 |
+
"loss": 0.7894,
|
775 |
+
"step": 106
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.3602693602693603,
|
779 |
+
"grad_norm": 0.6171875,
|
780 |
+
"learning_rate": 9.864113286481237e-06,
|
781 |
+
"loss": 0.7807,
|
782 |
+
"step": 107
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.36363636363636365,
|
786 |
+
"grad_norm": 1.015625,
|
787 |
+
"learning_rate": 9.859785620867197e-06,
|
788 |
+
"loss": 0.7895,
|
789 |
+
"step": 108
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.367003367003367,
|
793 |
+
"grad_norm": 1.0625,
|
794 |
+
"learning_rate": 9.855391097844671e-06,
|
795 |
+
"loss": 0.7936,
|
796 |
+
"step": 109
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.37037037037037035,
|
800 |
+
"grad_norm": 0.8984375,
|
801 |
+
"learning_rate": 9.850929777870324e-06,
|
802 |
+
"loss": 0.8024,
|
803 |
+
"step": 110
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 0.37373737373737376,
|
807 |
+
"grad_norm": 0.6640625,
|
808 |
+
"learning_rate": 9.846401722319759e-06,
|
809 |
+
"loss": 0.7542,
|
810 |
+
"step": 111
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.3771043771043771,
|
814 |
+
"grad_norm": 1.1640625,
|
815 |
+
"learning_rate": 9.841806993486686e-06,
|
816 |
+
"loss": 0.7689,
|
817 |
+
"step": 112
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.38047138047138046,
|
821 |
+
"grad_norm": 0.765625,
|
822 |
+
"learning_rate": 9.837145654582055e-06,
|
823 |
+
"loss": 0.7133,
|
824 |
+
"step": 113
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.3838383838383838,
|
828 |
+
"grad_norm": 0.87109375,
|
829 |
+
"learning_rate": 9.832417769733185e-06,
|
830 |
+
"loss": 0.795,
|
831 |
+
"step": 114
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.3838383838383838,
|
835 |
+
"eval_loss": 0.7676474452018738,
|
836 |
+
"eval_runtime": 8.7789,
|
837 |
+
"eval_samples_per_second": 56.955,
|
838 |
+
"eval_steps_per_second": 3.645,
|
839 |
+
"step": 114
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 0.3872053872053872,
|
843 |
+
"grad_norm": 0.86328125,
|
844 |
+
"learning_rate": 9.827623403982893e-06,
|
845 |
+
"loss": 0.7992,
|
846 |
+
"step": 115
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.39057239057239057,
|
850 |
+
"grad_norm": 0.7421875,
|
851 |
+
"learning_rate": 9.822762623288584e-06,
|
852 |
+
"loss": 0.7678,
|
853 |
+
"step": 116
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.3939393939393939,
|
857 |
+
"grad_norm": 0.85546875,
|
858 |
+
"learning_rate": 9.81783549452136e-06,
|
859 |
+
"loss": 0.7861,
|
860 |
+
"step": 117
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.39730639730639733,
|
864 |
+
"grad_norm": 0.71484375,
|
865 |
+
"learning_rate": 9.812842085465086e-06,
|
866 |
+
"loss": 0.7447,
|
867 |
+
"step": 118
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.4006734006734007,
|
871 |
+
"grad_norm": 0.5703125,
|
872 |
+
"learning_rate": 9.807782464815463e-06,
|
873 |
+
"loss": 0.7218,
|
874 |
+
"step": 119
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.40404040404040403,
|
878 |
+
"grad_norm": 0.6171875,
|
879 |
+
"learning_rate": 9.802656702179088e-06,
|
880 |
+
"loss": 0.7637,
|
881 |
+
"step": 120
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 0.4074074074074074,
|
885 |
+
"grad_norm": 0.54296875,
|
886 |
+
"learning_rate": 9.797464868072489e-06,
|
887 |
+
"loss": 0.7588,
|
888 |
+
"step": 121
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.4107744107744108,
|
892 |
+
"grad_norm": 0.6171875,
|
893 |
+
"learning_rate": 9.792207033921152e-06,
|
894 |
+
"loss": 0.7539,
|
895 |
+
"step": 122
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.41414141414141414,
|
899 |
+
"grad_norm": 0.8046875,
|
900 |
+
"learning_rate": 9.786883272058554e-06,
|
901 |
+
"loss": 0.7524,
|
902 |
+
"step": 123
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.4175084175084175,
|
906 |
+
"grad_norm": 0.6953125,
|
907 |
+
"learning_rate": 9.781493655725149e-06,
|
908 |
+
"loss": 0.731,
|
909 |
+
"step": 124
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.4208754208754209,
|
913 |
+
"grad_norm": 0.64453125,
|
914 |
+
"learning_rate": 9.776038259067375e-06,
|
915 |
+
"loss": 0.8022,
|
916 |
+
"step": 125
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.42424242424242425,
|
920 |
+
"grad_norm": 0.48046875,
|
921 |
+
"learning_rate": 9.770517157136625e-06,
|
922 |
+
"loss": 0.7528,
|
923 |
+
"step": 126
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.4276094276094276,
|
927 |
+
"grad_norm": 0.5546875,
|
928 |
+
"learning_rate": 9.764930425888216e-06,
|
929 |
+
"loss": 0.7037,
|
930 |
+
"step": 127
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.43097643097643096,
|
934 |
+
"grad_norm": 0.546875,
|
935 |
+
"learning_rate": 9.759278142180348e-06,
|
936 |
+
"loss": 0.7519,
|
937 |
+
"step": 128
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 0.43434343434343436,
|
941 |
+
"grad_norm": 0.61328125,
|
942 |
+
"learning_rate": 9.753560383773046e-06,
|
943 |
+
"loss": 0.8163,
|
944 |
+
"step": 129
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.4377104377104377,
|
948 |
+
"grad_norm": 0.53125,
|
949 |
+
"learning_rate": 9.747777229327085e-06,
|
950 |
+
"loss": 0.7292,
|
951 |
+
"step": 130
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.44107744107744107,
|
955 |
+
"grad_norm": 0.58203125,
|
956 |
+
"learning_rate": 9.741928758402912e-06,
|
957 |
+
"loss": 0.7351,
|
958 |
+
"step": 131
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 0.4444444444444444,
|
962 |
+
"grad_norm": 0.5234375,
|
963 |
+
"learning_rate": 9.736015051459551e-06,
|
964 |
+
"loss": 0.7429,
|
965 |
+
"step": 132
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.4478114478114478,
|
969 |
+
"grad_norm": 0.65234375,
|
970 |
+
"learning_rate": 9.730036189853497e-06,
|
971 |
+
"loss": 0.7616,
|
972 |
+
"step": 133
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.4511784511784512,
|
976 |
+
"grad_norm": 0.53125,
|
977 |
+
"learning_rate": 9.723992255837596e-06,
|
978 |
+
"loss": 0.7263,
|
979 |
+
"step": 134
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 0.45454545454545453,
|
983 |
+
"grad_norm": 0.5546875,
|
984 |
+
"learning_rate": 9.717883332559911e-06,
|
985 |
+
"loss": 0.7427,
|
986 |
+
"step": 135
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.45791245791245794,
|
990 |
+
"grad_norm": 0.66796875,
|
991 |
+
"learning_rate": 9.71170950406258e-06,
|
992 |
+
"loss": 0.7261,
|
993 |
+
"step": 136
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.4612794612794613,
|
997 |
+
"grad_norm": 0.58984375,
|
998 |
+
"learning_rate": 9.705470855280661e-06,
|
999 |
+
"loss": 0.754,
|
1000 |
+
"step": 137
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.46464646464646464,
|
1004 |
+
"grad_norm": 0.6015625,
|
1005 |
+
"learning_rate": 9.699167472040965e-06,
|
1006 |
+
"loss": 0.7554,
|
1007 |
+
"step": 138
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 0.468013468013468,
|
1011 |
+
"grad_norm": 0.5546875,
|
1012 |
+
"learning_rate": 9.692799441060868e-06,
|
1013 |
+
"loss": 0.7488,
|
1014 |
+
"step": 139
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.4713804713804714,
|
1018 |
+
"grad_norm": 0.53125,
|
1019 |
+
"learning_rate": 9.686366849947126e-06,
|
1020 |
+
"loss": 0.7066,
|
1021 |
+
"step": 140
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 0.47474747474747475,
|
1025 |
+
"grad_norm": 0.55078125,
|
1026 |
+
"learning_rate": 9.679869787194664e-06,
|
1027 |
+
"loss": 0.7818,
|
1028 |
+
"step": 141
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.4781144781144781,
|
1032 |
+
"grad_norm": 0.4765625,
|
1033 |
+
"learning_rate": 9.673308342185366e-06,
|
1034 |
+
"loss": 0.7289,
|
1035 |
+
"step": 142
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.48148148148148145,
|
1039 |
+
"grad_norm": 0.62109375,
|
1040 |
+
"learning_rate": 9.666682605186834e-06,
|
1041 |
+
"loss": 0.7301,
|
1042 |
+
"step": 143
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.48484848484848486,
|
1046 |
+
"grad_norm": 0.54296875,
|
1047 |
+
"learning_rate": 9.659992667351157e-06,
|
1048 |
+
"loss": 0.7673,
|
1049 |
+
"step": 144
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 0.4882154882154882,
|
1053 |
+
"grad_norm": 0.486328125,
|
1054 |
+
"learning_rate": 9.653238620713652e-06,
|
1055 |
+
"loss": 0.6884,
|
1056 |
+
"step": 145
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 0.49158249158249157,
|
1060 |
+
"grad_norm": 0.6484375,
|
1061 |
+
"learning_rate": 9.646420558191596e-06,
|
1062 |
+
"loss": 0.7043,
|
1063 |
+
"step": 146
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 0.494949494949495,
|
1067 |
+
"grad_norm": 0.51171875,
|
1068 |
+
"learning_rate": 9.639538573582952e-06,
|
1069 |
+
"loss": 0.7122,
|
1070 |
+
"step": 147
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.4983164983164983,
|
1074 |
+
"grad_norm": 0.498046875,
|
1075 |
+
"learning_rate": 9.632592761565078e-06,
|
1076 |
+
"loss": 0.7232,
|
1077 |
+
"step": 148
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.5016835016835017,
|
1081 |
+
"grad_norm": 0.5625,
|
1082 |
+
"learning_rate": 9.625583217693419e-06,
|
1083 |
+
"loss": 0.7311,
|
1084 |
+
"step": 149
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 0.5050505050505051,
|
1088 |
+
"grad_norm": 0.63671875,
|
1089 |
+
"learning_rate": 9.618510038400203e-06,
|
1090 |
+
"loss": 0.7322,
|
1091 |
+
"step": 150
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 0.5084175084175084,
|
1095 |
+
"grad_norm": 0.75390625,
|
1096 |
+
"learning_rate": 9.611373320993104e-06,
|
1097 |
+
"loss": 0.6983,
|
1098 |
+
"step": 151
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 0.5117845117845118,
|
1102 |
+
"grad_norm": 0.53125,
|
1103 |
+
"learning_rate": 9.604173163653906e-06,
|
1104 |
+
"loss": 0.6999,
|
1105 |
+
"step": 152
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 0.5117845117845118,
|
1109 |
+
"eval_loss": 0.7242563366889954,
|
1110 |
+
"eval_runtime": 8.7081,
|
1111 |
+
"eval_samples_per_second": 57.418,
|
1112 |
+
"eval_steps_per_second": 3.675,
|
1113 |
+
"step": 152
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.5151515151515151,
|
1117 |
+
"grad_norm": 0.55859375,
|
1118 |
+
"learning_rate": 9.596909665437155e-06,
|
1119 |
+
"loss": 0.7469,
|
1120 |
+
"step": 153
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 0.5185185185185185,
|
1124 |
+
"grad_norm": 0.5078125,
|
1125 |
+
"learning_rate": 9.589582926268798e-06,
|
1126 |
+
"loss": 0.7176,
|
1127 |
+
"step": 154
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 0.5218855218855218,
|
1131 |
+
"grad_norm": 0.4921875,
|
1132 |
+
"learning_rate": 9.582193046944799e-06,
|
1133 |
+
"loss": 0.7455,
|
1134 |
+
"step": 155
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.5252525252525253,
|
1138 |
+
"grad_norm": 0.51171875,
|
1139 |
+
"learning_rate": 9.574740129129767e-06,
|
1140 |
+
"loss": 0.7204,
|
1141 |
+
"step": 156
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 0.5286195286195287,
|
1145 |
+
"grad_norm": 0.474609375,
|
1146 |
+
"learning_rate": 9.567224275355538e-06,
|
1147 |
+
"loss": 0.7321,
|
1148 |
+
"step": 157
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.531986531986532,
|
1152 |
+
"grad_norm": 0.53125,
|
1153 |
+
"learning_rate": 9.559645589019787e-06,
|
1154 |
+
"loss": 0.7455,
|
1155 |
+
"step": 158
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.5353535353535354,
|
1159 |
+
"grad_norm": 0.494140625,
|
1160 |
+
"learning_rate": 9.552004174384582e-06,
|
1161 |
+
"loss": 0.7464,
|
1162 |
+
"step": 159
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 0.5387205387205387,
|
1166 |
+
"grad_norm": 0.5234375,
|
1167 |
+
"learning_rate": 9.544300136574973e-06,
|
1168 |
+
"loss": 0.7138,
|
1169 |
+
"step": 160
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 0.5420875420875421,
|
1173 |
+
"grad_norm": 0.59375,
|
1174 |
+
"learning_rate": 9.536533581577526e-06,
|
1175 |
+
"loss": 0.7321,
|
1176 |
+
"step": 161
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 0.5454545454545454,
|
1180 |
+
"grad_norm": 0.57421875,
|
1181 |
+
"learning_rate": 9.528704616238875e-06,
|
1182 |
+
"loss": 0.7205,
|
1183 |
+
"step": 162
|
1184 |
+
},
|
1185 |
+
{
|
1186 |
+
"epoch": 0.5488215488215489,
|
1187 |
+
"grad_norm": 0.484375,
|
1188 |
+
"learning_rate": 9.520813348264252e-06,
|
1189 |
+
"loss": 0.7107,
|
1190 |
+
"step": 163
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 0.5521885521885522,
|
1194 |
+
"grad_norm": 0.455078125,
|
1195 |
+
"learning_rate": 9.512859886216003e-06,
|
1196 |
+
"loss": 0.6975,
|
1197 |
+
"step": 164
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.5555555555555556,
|
1201 |
+
"grad_norm": 0.46875,
|
1202 |
+
"learning_rate": 9.504844339512096e-06,
|
1203 |
+
"loss": 0.7209,
|
1204 |
+
"step": 165
|
1205 |
+
},
|
1206 |
+
{
|
1207 |
+
"epoch": 0.5589225589225589,
|
1208 |
+
"grad_norm": 0.50390625,
|
1209 |
+
"learning_rate": 9.496766818424612e-06,
|
1210 |
+
"loss": 0.6932,
|
1211 |
+
"step": 166
|
1212 |
+
},
|
1213 |
+
{
|
1214 |
+
"epoch": 0.5622895622895623,
|
1215 |
+
"grad_norm": 0.69140625,
|
1216 |
+
"learning_rate": 9.488627434078232e-06,
|
1217 |
+
"loss": 0.6676,
|
1218 |
+
"step": 167
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 0.5656565656565656,
|
1222 |
+
"grad_norm": 0.443359375,
|
1223 |
+
"learning_rate": 9.480426298448706e-06,
|
1224 |
+
"loss": 0.6909,
|
1225 |
+
"step": 168
|
1226 |
+
},
|
1227 |
+
{
|
1228 |
+
"epoch": 0.569023569023569,
|
1229 |
+
"grad_norm": 0.4609375,
|
1230 |
+
"learning_rate": 9.472163524361317e-06,
|
1231 |
+
"loss": 0.7142,
|
1232 |
+
"step": 169
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.5723905723905723,
|
1236 |
+
"grad_norm": 0.474609375,
|
1237 |
+
"learning_rate": 9.46383922548932e-06,
|
1238 |
+
"loss": 0.7168,
|
1239 |
+
"step": 170
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.5757575757575758,
|
1243 |
+
"grad_norm": 0.435546875,
|
1244 |
+
"learning_rate": 9.455453516352385e-06,
|
1245 |
+
"loss": 0.6618,
|
1246 |
+
"step": 171
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 0.5791245791245792,
|
1250 |
+
"grad_norm": 0.45703125,
|
1251 |
+
"learning_rate": 9.447006512315025e-06,
|
1252 |
+
"loss": 0.694,
|
1253 |
+
"step": 172
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 0.5824915824915825,
|
1257 |
+
"grad_norm": 0.59765625,
|
1258 |
+
"learning_rate": 9.438498329584995e-06,
|
1259 |
+
"loss": 0.6858,
|
1260 |
+
"step": 173
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 0.5858585858585859,
|
1264 |
+
"grad_norm": 0.48046875,
|
1265 |
+
"learning_rate": 9.429929085211711e-06,
|
1266 |
+
"loss": 0.7419,
|
1267 |
+
"step": 174
|
1268 |
+
},
|
1269 |
+
{
|
1270 |
+
"epoch": 0.5892255892255892,
|
1271 |
+
"grad_norm": 0.4375,
|
1272 |
+
"learning_rate": 9.421298897084622e-06,
|
1273 |
+
"loss": 0.6734,
|
1274 |
+
"step": 175
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.5925925925925926,
|
1278 |
+
"grad_norm": 0.494140625,
|
1279 |
+
"learning_rate": 9.412607883931608e-06,
|
1280 |
+
"loss": 0.7188,
|
1281 |
+
"step": 176
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 0.5959595959595959,
|
1285 |
+
"grad_norm": 0.41796875,
|
1286 |
+
"learning_rate": 9.403856165317322e-06,
|
1287 |
+
"loss": 0.6732,
|
1288 |
+
"step": 177
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"epoch": 0.5993265993265994,
|
1292 |
+
"grad_norm": 0.59765625,
|
1293 |
+
"learning_rate": 9.39504386164157e-06,
|
1294 |
+
"loss": 0.6594,
|
1295 |
+
"step": 178
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 0.6026936026936027,
|
1299 |
+
"grad_norm": 0.490234375,
|
1300 |
+
"learning_rate": 9.38617109413764e-06,
|
1301 |
+
"loss": 0.7153,
|
1302 |
+
"step": 179
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 0.6060606060606061,
|
1306 |
+
"grad_norm": 0.60546875,
|
1307 |
+
"learning_rate": 9.377237984870636e-06,
|
1308 |
+
"loss": 0.6762,
|
1309 |
+
"step": 180
|
1310 |
+
},
|
1311 |
+
{
|
1312 |
+
"epoch": 0.6094276094276094,
|
1313 |
+
"grad_norm": 0.53125,
|
1314 |
+
"learning_rate": 9.3682446567358e-06,
|
1315 |
+
"loss": 0.6839,
|
1316 |
+
"step": 181
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 0.6127946127946128,
|
1320 |
+
"grad_norm": 0.515625,
|
1321 |
+
"learning_rate": 9.359191233456821e-06,
|
1322 |
+
"loss": 0.6949,
|
1323 |
+
"step": 182
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 0.6161616161616161,
|
1327 |
+
"grad_norm": 0.50390625,
|
1328 |
+
"learning_rate": 9.350077839584139e-06,
|
1329 |
+
"loss": 0.7045,
|
1330 |
+
"step": 183
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.6195286195286195,
|
1334 |
+
"grad_norm": 0.42578125,
|
1335 |
+
"learning_rate": 9.34090460049322e-06,
|
1336 |
+
"loss": 0.668,
|
1337 |
+
"step": 184
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 0.622895622895623,
|
1341 |
+
"grad_norm": 0.54296875,
|
1342 |
+
"learning_rate": 9.33167164238284e-06,
|
1343 |
+
"loss": 0.7144,
|
1344 |
+
"step": 185
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.6262626262626263,
|
1348 |
+
"grad_norm": 0.44921875,
|
1349 |
+
"learning_rate": 9.322379092273345e-06,
|
1350 |
+
"loss": 0.7084,
|
1351 |
+
"step": 186
|
1352 |
+
},
|
1353 |
+
{
|
1354 |
+
"epoch": 0.6296296296296297,
|
1355 |
+
"grad_norm": 0.427734375,
|
1356 |
+
"learning_rate": 9.313027078004903e-06,
|
1357 |
+
"loss": 0.7555,
|
1358 |
+
"step": 187
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 0.632996632996633,
|
1362 |
+
"grad_norm": 0.44140625,
|
1363 |
+
"learning_rate": 9.303615728235753e-06,
|
1364 |
+
"loss": 0.6963,
|
1365 |
+
"step": 188
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 0.6363636363636364,
|
1369 |
+
"grad_norm": 0.515625,
|
1370 |
+
"learning_rate": 9.29414517244042e-06,
|
1371 |
+
"loss": 0.6785,
|
1372 |
+
"step": 189
|
1373 |
+
},
|
1374 |
+
{
|
1375 |
+
"epoch": 0.6397306397306397,
|
1376 |
+
"grad_norm": 0.5078125,
|
1377 |
+
"learning_rate": 9.284615540907947e-06,
|
1378 |
+
"loss": 0.7246,
|
1379 |
+
"step": 190
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 0.6397306397306397,
|
1383 |
+
"eval_loss": 0.6989265084266663,
|
1384 |
+
"eval_runtime": 8.6934,
|
1385 |
+
"eval_samples_per_second": 57.515,
|
1386 |
+
"eval_steps_per_second": 3.681,
|
1387 |
+
"step": 190
|
1388 |
+
},
|
1389 |
+
{
|
1390 |
+
"epoch": 0.6430976430976431,
|
1391 |
+
"grad_norm": 0.54296875,
|
1392 |
+
"learning_rate": 9.275026964740101e-06,
|
1393 |
+
"loss": 0.6995,
|
1394 |
+
"step": 191
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 0.6464646464646465,
|
1398 |
+
"grad_norm": 0.427734375,
|
1399 |
+
"learning_rate": 9.265379575849561e-06,
|
1400 |
+
"loss": 0.6988,
|
1401 |
+
"step": 192
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 0.6498316498316499,
|
1405 |
+
"grad_norm": 0.48046875,
|
1406 |
+
"learning_rate": 9.255673506958114e-06,
|
1407 |
+
"loss": 0.6569,
|
1408 |
+
"step": 193
|
1409 |
+
},
|
1410 |
+
{
|
1411 |
+
"epoch": 0.6531986531986532,
|
1412 |
+
"grad_norm": 0.486328125,
|
1413 |
+
"learning_rate": 9.245908891594818e-06,
|
1414 |
+
"loss": 0.6645,
|
1415 |
+
"step": 194
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"epoch": 0.6565656565656566,
|
1419 |
+
"grad_norm": 0.58984375,
|
1420 |
+
"learning_rate": 9.236085864094178e-06,
|
1421 |
+
"loss": 0.6745,
|
1422 |
+
"step": 195
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 0.6599326599326599,
|
1426 |
+
"grad_norm": 0.609375,
|
1427 |
+
"learning_rate": 9.226204559594284e-06,
|
1428 |
+
"loss": 0.7157,
|
1429 |
+
"step": 196
|
1430 |
+
},
|
1431 |
+
{
|
1432 |
+
"epoch": 0.6632996632996633,
|
1433 |
+
"grad_norm": 0.59375,
|
1434 |
+
"learning_rate": 9.216265114034964e-06,
|
1435 |
+
"loss": 0.7298,
|
1436 |
+
"step": 197
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 0.6666666666666666,
|
1440 |
+
"grad_norm": 0.451171875,
|
1441 |
+
"learning_rate": 9.206267664155906e-06,
|
1442 |
+
"loss": 0.6439,
|
1443 |
+
"step": 198
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.67003367003367,
|
1447 |
+
"grad_norm": 0.447265625,
|
1448 |
+
"learning_rate": 9.19621234749478e-06,
|
1449 |
+
"loss": 0.6719,
|
1450 |
+
"step": 199
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 0.6734006734006734,
|
1454 |
+
"grad_norm": 0.41796875,
|
1455 |
+
"learning_rate": 9.186099302385345e-06,
|
1456 |
+
"loss": 0.6496,
|
1457 |
+
"step": 200
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 0.6767676767676768,
|
1461 |
+
"grad_norm": 0.482421875,
|
1462 |
+
"learning_rate": 9.175928667955547e-06,
|
1463 |
+
"loss": 0.709,
|
1464 |
+
"step": 201
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.6801346801346801,
|
1468 |
+
"grad_norm": 0.50390625,
|
1469 |
+
"learning_rate": 9.1657005841256e-06,
|
1470 |
+
"loss": 0.7054,
|
1471 |
+
"step": 202
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 0.6835016835016835,
|
1475 |
+
"grad_norm": 0.455078125,
|
1476 |
+
"learning_rate": 9.155415191606074e-06,
|
1477 |
+
"loss": 0.6941,
|
1478 |
+
"step": 203
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 0.6868686868686869,
|
1482 |
+
"grad_norm": 0.53515625,
|
1483 |
+
"learning_rate": 9.145072631895942e-06,
|
1484 |
+
"loss": 0.6919,
|
1485 |
+
"step": 204
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 0.6902356902356902,
|
1489 |
+
"grad_norm": 0.62890625,
|
1490 |
+
"learning_rate": 9.134673047280644e-06,
|
1491 |
+
"loss": 0.7098,
|
1492 |
+
"step": 205
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 0.6936026936026936,
|
1496 |
+
"grad_norm": 0.546875,
|
1497 |
+
"learning_rate": 9.12421658083013e-06,
|
1498 |
+
"loss": 0.6902,
|
1499 |
+
"step": 206
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 0.696969696969697,
|
1503 |
+
"grad_norm": 0.58984375,
|
1504 |
+
"learning_rate": 9.113703376396885e-06,
|
1505 |
+
"loss": 0.7228,
|
1506 |
+
"step": 207
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 0.7003367003367004,
|
1510 |
+
"grad_norm": 0.484375,
|
1511 |
+
"learning_rate": 9.103133578613959e-06,
|
1512 |
+
"loss": 0.6961,
|
1513 |
+
"step": 208
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 0.7037037037037037,
|
1517 |
+
"grad_norm": 0.515625,
|
1518 |
+
"learning_rate": 9.092507332892968e-06,
|
1519 |
+
"loss": 0.6689,
|
1520 |
+
"step": 209
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 0.7070707070707071,
|
1524 |
+
"grad_norm": 0.5390625,
|
1525 |
+
"learning_rate": 9.081824785422099e-06,
|
1526 |
+
"loss": 0.6552,
|
1527 |
+
"step": 210
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 0.7104377104377104,
|
1531 |
+
"grad_norm": 0.462890625,
|
1532 |
+
"learning_rate": 9.071086083164099e-06,
|
1533 |
+
"loss": 0.6739,
|
1534 |
+
"step": 211
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 0.7138047138047138,
|
1538 |
+
"grad_norm": 0.435546875,
|
1539 |
+
"learning_rate": 9.060291373854252e-06,
|
1540 |
+
"loss": 0.699,
|
1541 |
+
"step": 212
|
1542 |
+
},
|
1543 |
+
{
|
1544 |
+
"epoch": 0.7171717171717171,
|
1545 |
+
"grad_norm": 0.49609375,
|
1546 |
+
"learning_rate": 9.04944080599834e-06,
|
1547 |
+
"loss": 0.6964,
|
1548 |
+
"step": 213
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 0.7205387205387206,
|
1552 |
+
"grad_norm": 0.47265625,
|
1553 |
+
"learning_rate": 9.038534528870618e-06,
|
1554 |
+
"loss": 0.678,
|
1555 |
+
"step": 214
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 0.7239057239057239,
|
1559 |
+
"grad_norm": 0.455078125,
|
1560 |
+
"learning_rate": 9.027572692511739e-06,
|
1561 |
+
"loss": 0.6847,
|
1562 |
+
"step": 215
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 0.7272727272727273,
|
1566 |
+
"grad_norm": 0.53515625,
|
1567 |
+
"learning_rate": 9.016555447726704e-06,
|
1568 |
+
"loss": 0.6811,
|
1569 |
+
"step": 216
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.7306397306397306,
|
1573 |
+
"grad_norm": 0.482421875,
|
1574 |
+
"learning_rate": 9.005482946082784e-06,
|
1575 |
+
"loss": 0.6831,
|
1576 |
+
"step": 217
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 0.734006734006734,
|
1580 |
+
"grad_norm": 0.474609375,
|
1581 |
+
"learning_rate": 8.994355339907429e-06,
|
1582 |
+
"loss": 0.6803,
|
1583 |
+
"step": 218
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 0.7373737373737373,
|
1587 |
+
"grad_norm": 0.443359375,
|
1588 |
+
"learning_rate": 8.98317278228618e-06,
|
1589 |
+
"loss": 0.6639,
|
1590 |
+
"step": 219
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 0.7407407407407407,
|
1594 |
+
"grad_norm": 0.474609375,
|
1595 |
+
"learning_rate": 8.971935427060563e-06,
|
1596 |
+
"loss": 0.6509,
|
1597 |
+
"step": 220
|
1598 |
+
},
|
1599 |
+
{
|
1600 |
+
"epoch": 0.7441077441077442,
|
1601 |
+
"grad_norm": 0.47265625,
|
1602 |
+
"learning_rate": 8.960643428825965e-06,
|
1603 |
+
"loss": 0.647,
|
1604 |
+
"step": 221
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 0.7474747474747475,
|
1608 |
+
"grad_norm": 0.498046875,
|
1609 |
+
"learning_rate": 8.949296942929515e-06,
|
1610 |
+
"loss": 0.6686,
|
1611 |
+
"step": 222
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.7508417508417509,
|
1615 |
+
"grad_norm": 0.5078125,
|
1616 |
+
"learning_rate": 8.937896125467941e-06,
|
1617 |
+
"loss": 0.6512,
|
1618 |
+
"step": 223
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 0.7542087542087542,
|
1622 |
+
"grad_norm": 0.60546875,
|
1623 |
+
"learning_rate": 8.92644113328543e-06,
|
1624 |
+
"loss": 0.6544,
|
1625 |
+
"step": 224
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 0.7575757575757576,
|
1629 |
+
"grad_norm": 0.474609375,
|
1630 |
+
"learning_rate": 8.91493212397146e-06,
|
1631 |
+
"loss": 0.7091,
|
1632 |
+
"step": 225
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 0.7609427609427609,
|
1636 |
+
"grad_norm": 0.515625,
|
1637 |
+
"learning_rate": 8.90336925585864e-06,
|
1638 |
+
"loss": 0.6522,
|
1639 |
+
"step": 226
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 0.7643097643097643,
|
1643 |
+
"grad_norm": 0.4375,
|
1644 |
+
"learning_rate": 8.891752688020532e-06,
|
1645 |
+
"loss": 0.6923,
|
1646 |
+
"step": 227
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 0.7676767676767676,
|
1650 |
+
"grad_norm": 0.47265625,
|
1651 |
+
"learning_rate": 8.880082580269454e-06,
|
1652 |
+
"loss": 0.6873,
|
1653 |
+
"step": 228
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 0.7676767676767676,
|
1657 |
+
"eval_loss": 0.6816474795341492,
|
1658 |
+
"eval_runtime": 8.7387,
|
1659 |
+
"eval_samples_per_second": 57.217,
|
1660 |
+
"eval_steps_per_second": 3.662,
|
1661 |
+
"step": 228
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.7710437710437711,
|
1665 |
+
"grad_norm": 0.466796875,
|
1666 |
+
"learning_rate": 8.868359093154292e-06,
|
1667 |
+
"loss": 0.6989,
|
1668 |
+
"step": 229
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.7744107744107744,
|
1672 |
+
"grad_norm": 0.4921875,
|
1673 |
+
"learning_rate": 8.856582387958286e-06,
|
1674 |
+
"loss": 0.6424,
|
1675 |
+
"step": 230
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.7777777777777778,
|
1679 |
+
"grad_norm": 0.546875,
|
1680 |
+
"learning_rate": 8.84475262669681e-06,
|
1681 |
+
"loss": 0.6477,
|
1682 |
+
"step": 231
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.7811447811447811,
|
1686 |
+
"grad_norm": 0.44921875,
|
1687 |
+
"learning_rate": 8.832869972115148e-06,
|
1688 |
+
"loss": 0.6623,
|
1689 |
+
"step": 232
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.7845117845117845,
|
1693 |
+
"grad_norm": 0.5625,
|
1694 |
+
"learning_rate": 8.820934587686247e-06,
|
1695 |
+
"loss": 0.6642,
|
1696 |
+
"step": 233
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.7878787878787878,
|
1700 |
+
"grad_norm": 0.470703125,
|
1701 |
+
"learning_rate": 8.808946637608476e-06,
|
1702 |
+
"loss": 0.6819,
|
1703 |
+
"step": 234
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.7912457912457912,
|
1707 |
+
"grad_norm": 0.470703125,
|
1708 |
+
"learning_rate": 8.796906286803366e-06,
|
1709 |
+
"loss": 0.7039,
|
1710 |
+
"step": 235
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.7946127946127947,
|
1714 |
+
"grad_norm": 0.51171875,
|
1715 |
+
"learning_rate": 8.784813700913336e-06,
|
1716 |
+
"loss": 0.7232,
|
1717 |
+
"step": 236
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.797979797979798,
|
1721 |
+
"grad_norm": 0.44140625,
|
1722 |
+
"learning_rate": 8.77266904629942e-06,
|
1723 |
+
"loss": 0.6687,
|
1724 |
+
"step": 237
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.8013468013468014,
|
1728 |
+
"grad_norm": 0.462890625,
|
1729 |
+
"learning_rate": 8.760472490038974e-06,
|
1730 |
+
"loss": 0.6664,
|
1731 |
+
"step": 238
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.8047138047138047,
|
1735 |
+
"grad_norm": 0.5234375,
|
1736 |
+
"learning_rate": 8.748224199923378e-06,
|
1737 |
+
"loss": 0.6752,
|
1738 |
+
"step": 239
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.8080808080808081,
|
1742 |
+
"grad_norm": 0.5078125,
|
1743 |
+
"learning_rate": 8.735924344455732e-06,
|
1744 |
+
"loss": 0.6373,
|
1745 |
+
"step": 240
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.8114478114478114,
|
1749 |
+
"grad_norm": 0.46484375,
|
1750 |
+
"learning_rate": 8.723573092848535e-06,
|
1751 |
+
"loss": 0.656,
|
1752 |
+
"step": 241
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.8148148148148148,
|
1756 |
+
"grad_norm": 0.46875,
|
1757 |
+
"learning_rate": 8.71117061502135e-06,
|
1758 |
+
"loss": 0.6747,
|
1759 |
+
"step": 242
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.8181818181818182,
|
1763 |
+
"grad_norm": 0.39453125,
|
1764 |
+
"learning_rate": 8.698717081598484e-06,
|
1765 |
+
"loss": 0.6878,
|
1766 |
+
"step": 243
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.8215488215488216,
|
1770 |
+
"grad_norm": 0.3984375,
|
1771 |
+
"learning_rate": 8.68621266390662e-06,
|
1772 |
+
"loss": 0.6381,
|
1773 |
+
"step": 244
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.8249158249158249,
|
1777 |
+
"grad_norm": 0.44140625,
|
1778 |
+
"learning_rate": 8.673657533972477e-06,
|
1779 |
+
"loss": 0.7127,
|
1780 |
+
"step": 245
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 0.8282828282828283,
|
1784 |
+
"grad_norm": 0.408203125,
|
1785 |
+
"learning_rate": 8.661051864520434e-06,
|
1786 |
+
"loss": 0.6888,
|
1787 |
+
"step": 246
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.8316498316498316,
|
1791 |
+
"grad_norm": 0.5078125,
|
1792 |
+
"learning_rate": 8.64839582897015e-06,
|
1793 |
+
"loss": 0.6444,
|
1794 |
+
"step": 247
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.835016835016835,
|
1798 |
+
"grad_norm": 0.42578125,
|
1799 |
+
"learning_rate": 8.635689601434197e-06,
|
1800 |
+
"loss": 0.6876,
|
1801 |
+
"step": 248
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.8383838383838383,
|
1805 |
+
"grad_norm": 0.6015625,
|
1806 |
+
"learning_rate": 8.622933356715639e-06,
|
1807 |
+
"loss": 0.7125,
|
1808 |
+
"step": 249
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.8417508417508418,
|
1812 |
+
"grad_norm": 0.51171875,
|
1813 |
+
"learning_rate": 8.61012727030565e-06,
|
1814 |
+
"loss": 0.6826,
|
1815 |
+
"step": 250
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.8451178451178452,
|
1819 |
+
"grad_norm": 0.435546875,
|
1820 |
+
"learning_rate": 8.597271518381083e-06,
|
1821 |
+
"loss": 0.6719,
|
1822 |
+
"step": 251
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.8484848484848485,
|
1826 |
+
"grad_norm": 0.609375,
|
1827 |
+
"learning_rate": 8.584366277802057e-06,
|
1828 |
+
"loss": 0.6723,
|
1829 |
+
"step": 252
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.8518518518518519,
|
1833 |
+
"grad_norm": 0.5546875,
|
1834 |
+
"learning_rate": 8.571411726109518e-06,
|
1835 |
+
"loss": 0.6899,
|
1836 |
+
"step": 253
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 0.8552188552188552,
|
1840 |
+
"grad_norm": 0.5078125,
|
1841 |
+
"learning_rate": 8.558408041522801e-06,
|
1842 |
+
"loss": 0.7042,
|
1843 |
+
"step": 254
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.8585858585858586,
|
1847 |
+
"grad_norm": 0.455078125,
|
1848 |
+
"learning_rate": 8.545355402937174e-06,
|
1849 |
+
"loss": 0.6429,
|
1850 |
+
"step": 255
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.8619528619528619,
|
1854 |
+
"grad_norm": 0.439453125,
|
1855 |
+
"learning_rate": 8.532253989921377e-06,
|
1856 |
+
"loss": 0.6586,
|
1857 |
+
"step": 256
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.8653198653198653,
|
1861 |
+
"grad_norm": 0.435546875,
|
1862 |
+
"learning_rate": 8.519103982715158e-06,
|
1863 |
+
"loss": 0.6212,
|
1864 |
+
"step": 257
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 0.8686868686868687,
|
1868 |
+
"grad_norm": 0.486328125,
|
1869 |
+
"learning_rate": 8.505905562226784e-06,
|
1870 |
+
"loss": 0.6421,
|
1871 |
+
"step": 258
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.8720538720538721,
|
1875 |
+
"grad_norm": 0.50390625,
|
1876 |
+
"learning_rate": 8.492658910030558e-06,
|
1877 |
+
"loss": 0.6051,
|
1878 |
+
"step": 259
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 0.8754208754208754,
|
1882 |
+
"grad_norm": 0.482421875,
|
1883 |
+
"learning_rate": 8.479364208364322e-06,
|
1884 |
+
"loss": 0.6454,
|
1885 |
+
"step": 260
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.8787878787878788,
|
1889 |
+
"grad_norm": 0.48046875,
|
1890 |
+
"learning_rate": 8.466021640126946e-06,
|
1891 |
+
"loss": 0.6579,
|
1892 |
+
"step": 261
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.8821548821548821,
|
1896 |
+
"grad_norm": 0.41015625,
|
1897 |
+
"learning_rate": 8.452631388875814e-06,
|
1898 |
+
"loss": 0.6046,
|
1899 |
+
"step": 262
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.8855218855218855,
|
1903 |
+
"grad_norm": 0.451171875,
|
1904 |
+
"learning_rate": 8.439193638824296e-06,
|
1905 |
+
"loss": 0.6481,
|
1906 |
+
"step": 263
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.8888888888888888,
|
1910 |
+
"grad_norm": 0.41796875,
|
1911 |
+
"learning_rate": 8.425708574839221e-06,
|
1912 |
+
"loss": 0.6418,
|
1913 |
+
"step": 264
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.8922558922558923,
|
1917 |
+
"grad_norm": 0.48046875,
|
1918 |
+
"learning_rate": 8.412176382438327e-06,
|
1919 |
+
"loss": 0.7079,
|
1920 |
+
"step": 265
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 0.8956228956228957,
|
1924 |
+
"grad_norm": 0.5078125,
|
1925 |
+
"learning_rate": 8.398597247787706e-06,
|
1926 |
+
"loss": 0.7014,
|
1927 |
+
"step": 266
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.8956228956228957,
|
1931 |
+
"eval_loss": 0.66867995262146,
|
1932 |
+
"eval_runtime": 8.7476,
|
1933 |
+
"eval_samples_per_second": 57.158,
|
1934 |
+
"eval_steps_per_second": 3.658,
|
1935 |
+
"step": 266
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.898989898989899,
|
1939 |
+
"grad_norm": 0.404296875,
|
1940 |
+
"learning_rate": 8.384971357699255e-06,
|
1941 |
+
"loss": 0.631,
|
1942 |
+
"step": 267
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 0.9023569023569024,
|
1946 |
+
"grad_norm": 0.484375,
|
1947 |
+
"learning_rate": 8.371298899628091e-06,
|
1948 |
+
"loss": 0.691,
|
1949 |
+
"step": 268
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 0.9057239057239057,
|
1953 |
+
"grad_norm": 0.421875,
|
1954 |
+
"learning_rate": 8.357580061669985e-06,
|
1955 |
+
"loss": 0.6443,
|
1956 |
+
"step": 269
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 0.9090909090909091,
|
1960 |
+
"grad_norm": 0.4296875,
|
1961 |
+
"learning_rate": 8.343815032558768e-06,
|
1962 |
+
"loss": 0.6683,
|
1963 |
+
"step": 270
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 0.9124579124579124,
|
1967 |
+
"grad_norm": 0.43359375,
|
1968 |
+
"learning_rate": 8.330004001663734e-06,
|
1969 |
+
"loss": 0.6208,
|
1970 |
+
"step": 271
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 0.9158249158249159,
|
1974 |
+
"grad_norm": 0.5078125,
|
1975 |
+
"learning_rate": 8.316147158987036e-06,
|
1976 |
+
"loss": 0.6554,
|
1977 |
+
"step": 272
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.9191919191919192,
|
1981 |
+
"grad_norm": 0.484375,
|
1982 |
+
"learning_rate": 8.30224469516107e-06,
|
1983 |
+
"loss": 0.6884,
|
1984 |
+
"step": 273
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 0.9225589225589226,
|
1988 |
+
"grad_norm": 0.451171875,
|
1989 |
+
"learning_rate": 8.288296801445863e-06,
|
1990 |
+
"loss": 0.6633,
|
1991 |
+
"step": 274
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 0.9259259259259259,
|
1995 |
+
"grad_norm": 0.462890625,
|
1996 |
+
"learning_rate": 8.274303669726427e-06,
|
1997 |
+
"loss": 0.6521,
|
1998 |
+
"step": 275
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 0.9292929292929293,
|
2002 |
+
"grad_norm": 0.462890625,
|
2003 |
+
"learning_rate": 8.260265492510121e-06,
|
2004 |
+
"loss": 0.6429,
|
2005 |
+
"step": 276
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 0.9326599326599326,
|
2009 |
+
"grad_norm": 0.4765625,
|
2010 |
+
"learning_rate": 8.246182462924022e-06,
|
2011 |
+
"loss": 0.6604,
|
2012 |
+
"step": 277
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 0.936026936026936,
|
2016 |
+
"grad_norm": 0.408203125,
|
2017 |
+
"learning_rate": 8.232054774712239e-06,
|
2018 |
+
"loss": 0.6438,
|
2019 |
+
"step": 278
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.9393939393939394,
|
2023 |
+
"grad_norm": 0.4375,
|
2024 |
+
"learning_rate": 8.217882622233268e-06,
|
2025 |
+
"loss": 0.6319,
|
2026 |
+
"step": 279
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 0.9427609427609428,
|
2030 |
+
"grad_norm": 0.5,
|
2031 |
+
"learning_rate": 8.203666200457312e-06,
|
2032 |
+
"loss": 0.6349,
|
2033 |
+
"step": 280
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 0.9461279461279462,
|
2037 |
+
"grad_norm": 0.45703125,
|
2038 |
+
"learning_rate": 8.1894057049636e-06,
|
2039 |
+
"loss": 0.6657,
|
2040 |
+
"step": 281
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 0.9494949494949495,
|
2044 |
+
"grad_norm": 0.423828125,
|
2045 |
+
"learning_rate": 8.175101331937692e-06,
|
2046 |
+
"loss": 0.6866,
|
2047 |
+
"step": 282
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 0.9528619528619529,
|
2051 |
+
"grad_norm": 0.4296875,
|
2052 |
+
"learning_rate": 8.160753278168787e-06,
|
2053 |
+
"loss": 0.6544,
|
2054 |
+
"step": 283
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 0.9562289562289562,
|
2058 |
+
"grad_norm": 0.482421875,
|
2059 |
+
"learning_rate": 8.146361741047007e-06,
|
2060 |
+
"loss": 0.676,
|
2061 |
+
"step": 284
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.9595959595959596,
|
2065 |
+
"grad_norm": 0.416015625,
|
2066 |
+
"learning_rate": 8.131926918560692e-06,
|
2067 |
+
"loss": 0.6102,
|
2068 |
+
"step": 285
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 0.9629629629629629,
|
2072 |
+
"grad_norm": 0.474609375,
|
2073 |
+
"learning_rate": 8.117449009293668e-06,
|
2074 |
+
"loss": 0.6865,
|
2075 |
+
"step": 286
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 0.9663299663299664,
|
2079 |
+
"grad_norm": 0.423828125,
|
2080 |
+
"learning_rate": 8.102928212422519e-06,
|
2081 |
+
"loss": 0.6298,
|
2082 |
+
"step": 287
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 0.9696969696969697,
|
2086 |
+
"grad_norm": 0.439453125,
|
2087 |
+
"learning_rate": 8.08836472771384e-06,
|
2088 |
+
"loss": 0.6789,
|
2089 |
+
"step": 288
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 0.9730639730639731,
|
2093 |
+
"grad_norm": 0.4453125,
|
2094 |
+
"learning_rate": 8.073758755521506e-06,
|
2095 |
+
"loss": 0.6157,
|
2096 |
+
"step": 289
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 0.9764309764309764,
|
2100 |
+
"grad_norm": 0.404296875,
|
2101 |
+
"learning_rate": 8.059110496783891e-06,
|
2102 |
+
"loss": 0.6269,
|
2103 |
+
"step": 290
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.9797979797979798,
|
2107 |
+
"grad_norm": 0.427734375,
|
2108 |
+
"learning_rate": 8.044420153021123e-06,
|
2109 |
+
"loss": 0.6405,
|
2110 |
+
"step": 291
|
2111 |
+
},
|
2112 |
+
{
|
2113 |
+
"epoch": 0.9831649831649831,
|
2114 |
+
"grad_norm": 0.46875,
|
2115 |
+
"learning_rate": 8.02968792633231e-06,
|
2116 |
+
"loss": 0.6657,
|
2117 |
+
"step": 292
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 0.9865319865319865,
|
2121 |
+
"grad_norm": 0.466796875,
|
2122 |
+
"learning_rate": 8.014914019392743e-06,
|
2123 |
+
"loss": 0.6373,
|
2124 |
+
"step": 293
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 0.98989898989899,
|
2128 |
+
"grad_norm": 0.59765625,
|
2129 |
+
"learning_rate": 8.00009863545113e-06,
|
2130 |
+
"loss": 0.6495,
|
2131 |
+
"step": 294
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 0.9932659932659933,
|
2135 |
+
"grad_norm": 0.478515625,
|
2136 |
+
"learning_rate": 7.985241978326786e-06,
|
2137 |
+
"loss": 0.6003,
|
2138 |
+
"step": 295
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 0.9966329966329966,
|
2142 |
+
"grad_norm": 0.40625,
|
2143 |
+
"learning_rate": 7.970344252406832e-06,
|
2144 |
+
"loss": 0.6543,
|
2145 |
+
"step": 296
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 1.0,
|
2149 |
+
"grad_norm": 0.6953125,
|
2150 |
+
"learning_rate": 7.955405662643384e-06,
|
2151 |
+
"loss": 0.6625,
|
2152 |
+
"step": 297
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 1.0033670033670035,
|
2156 |
+
"grad_norm": 0.412109375,
|
2157 |
+
"learning_rate": 7.940426414550732e-06,
|
2158 |
+
"loss": 0.6776,
|
2159 |
+
"step": 298
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 1.0067340067340067,
|
2163 |
+
"grad_norm": 0.419921875,
|
2164 |
+
"learning_rate": 7.925406714202518e-06,
|
2165 |
+
"loss": 0.6661,
|
2166 |
+
"step": 299
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 1.0101010101010102,
|
2170 |
+
"grad_norm": 0.4609375,
|
2171 |
+
"learning_rate": 7.910346768228893e-06,
|
2172 |
+
"loss": 0.6743,
|
2173 |
+
"step": 300
|
2174 |
+
}
|
2175 |
+
],
|
2176 |
+
"logging_steps": 1,
|
2177 |
+
"max_steps": 891,
|
2178 |
+
"num_input_tokens_seen": 0,
|
2179 |
+
"num_train_epochs": 3,
|
2180 |
+
"save_steps": 75,
|
2181 |
+
"stateful_callbacks": {
|
2182 |
+
"TrainerControl": {
|
2183 |
+
"args": {
|
2184 |
+
"should_epoch_stop": false,
|
2185 |
+
"should_evaluate": false,
|
2186 |
+
"should_log": false,
|
2187 |
+
"should_save": true,
|
2188 |
+
"should_training_stop": false
|
2189 |
+
},
|
2190 |
+
"attributes": {}
|
2191 |
+
}
|
2192 |
+
},
|
2193 |
+
"total_flos": 5.45750689775616e+17,
|
2194 |
+
"train_batch_size": 2,
|
2195 |
+
"trial_name": null,
|
2196 |
+
"trial_params": null
|
2197 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67281bdc6cc564e812aa4cb73613aaae3277625d9bdb71d00a737b9619706f71
|
3 |
+
size 6328
|