Commit
β’
10c8a05
1
Parent(s):
8560e14
Training in progress, step 600
Browse files- checkpoint-200/latest +0 -1
- {checkpoint-200 β checkpoint-600}/config.json +0 -0
- {checkpoint-200 β checkpoint-600}/generation_config.json +0 -0
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_0_mp_rank_00_model_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_1_mp_rank_00_model_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_2_mp_rank_00_model_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_3_mp_rank_00_model_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_4_mp_rank_00_model_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_5_mp_rank_00_model_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_6_mp_rank_00_model_states.pt +1 -1
- {checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_7_mp_rank_00_model_states.pt +1 -1
- checkpoint-600/latest +1 -0
- {checkpoint-200 β checkpoint-600}/model-00001-of-00002.safetensors +1 -1
- {checkpoint-200 β checkpoint-600}/model-00002-of-00002.safetensors +1 -1
- {checkpoint-200 β checkpoint-600}/model.safetensors.index.json +0 -0
- {checkpoint-200 β checkpoint-600}/rng_state_0.pth +0 -0
- {checkpoint-200 β checkpoint-600}/rng_state_1.pth +0 -0
- {checkpoint-200 β checkpoint-600}/rng_state_2.pth +0 -0
- {checkpoint-200 β checkpoint-600}/rng_state_3.pth +0 -0
- {checkpoint-200 β checkpoint-600}/rng_state_4.pth +0 -0
- {checkpoint-200 β checkpoint-600}/rng_state_5.pth +0 -0
- {checkpoint-200 β checkpoint-600}/rng_state_6.pth +0 -0
- {checkpoint-200 β checkpoint-600}/rng_state_7.pth +0 -0
- {checkpoint-200 β checkpoint-600}/special_tokens_map.json +0 -0
- {checkpoint-200 β checkpoint-600}/tokenizer.json +0 -0
- {checkpoint-200 β checkpoint-600}/tokenizer.model +0 -0
- {checkpoint-200 β checkpoint-600}/tokenizer_config.json +0 -0
- {checkpoint-200 β checkpoint-600}/trainer_state.json +243 -3
- {checkpoint-200 β checkpoint-600}/training_args.bin +0 -0
- {checkpoint-200 β checkpoint-600}/zero_to_fp32.py +0 -0
- runs/Aug22_18-42-03_ip-26-0-150-12/events.out.tfevents.1692729850.ip-26-0-150-12.2895584.0 +2 -2
checkpoint-200/latest
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
global_step200
|
|
|
|
{checkpoint-200 β checkpoint-600}/config.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/generation_config.json
RENAMED
File without changes
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66eb01a0e90463b9da96b92c71aa113fb0cc395d468d494cbaaf30b0c996c900
|
3 |
size 10107626487
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a9c27857331e866aa180ca994d30ecdeb152ce200686244186589fd2b6c5399
|
3 |
size 10107626487
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94cc70fd746640a3708551bd27076cca0c4493fc0ec627adc422dc06e217b4f1
|
3 |
size 10107626487
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53f785e4989207b0d802f03d21811f0310e6887f491becf18aab59dc2a8e34dc
|
3 |
size 10107626487
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:055b189cd86f4ab7885ffd7733ca11939b1c02c7b961887c23ff3765b85b2c26
|
3 |
size 10107626487
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b598e84707f1b589d6e34c06fddfcfd1c635efdeb8c34cf5ca13a510f0949837
|
3 |
size 10107626487
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15519b6df3b12db386d8c11e652af04badf693c055d7c3d49091aad19745e337
|
3 |
size 10107626487
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a17fc5b79f53abceedb3cc4c49fba56335c0c00a6ffa5320a11cacac9ad4e106
|
3 |
size 10107626487
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_0_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c17dd6ac6428c5d94c99148aa50c12df93df8b2462cbf19e8e84d9d333fcbd1e
|
3 |
size 168086
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_1_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dade817edf76921be5c0796cbcfdf915c904c183acf9c931777f623390eb1f3
|
3 |
size 168086
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_2_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87c1c5de42abbdea85c5b809d6ad1ea6ea81c0292569eae30054d35b7568f9e0
|
3 |
size 168086
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_3_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d2bc5f999fb8ccc85ce968f9308e1832cc481d0a36fbfee21231ee0251223b9
|
3 |
size 168086
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_4_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:287d7ae815a009508c9d5763cdb2b95cdccbcb41047461ddb5942fe4be828cd4
|
3 |
size 168086
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_5_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c563d457d97887b6b8ebca491ddbbb5f7d02940671baa85e856e70f2373dd1e8
|
3 |
size 168086
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_6_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbaa5dfcd7813a949984070a065f4d96fd979a8486c397c0fe82e466df55719e
|
3 |
size 168086
|
{checkpoint-200/global_step200 β checkpoint-600/global_step600}/zero_pp_rank_7_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cfe0ea806988e2741a7bc673de2fae1d546b08c34f0cf088d122f77c3098bac
|
3 |
size 168086
|
checkpoint-600/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step600
|
{checkpoint-200 β checkpoint-600}/model-00001-of-00002.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9976576392
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d5217aa0cdf2a3e998ac2276247c8b950f52424ef53ba6bedbb47fe566772c4
|
3 |
size 9976576392
|
{checkpoint-200 β checkpoint-600}/model-00002-of-00002.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3500296504
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15c35bdf2b64df17b13e8aa89bf76a22e3fe647fb7a427d6d581f7b18dbbea71
|
3 |
size 3500296504
|
{checkpoint-200 β checkpoint-600}/model.safetensors.index.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/rng_state_0.pth
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/rng_state_1.pth
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/rng_state_2.pth
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/rng_state_3.pth
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/rng_state_4.pth
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/rng_state_5.pth
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/rng_state_6.pth
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/rng_state_7.pth
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/special_tokens_map.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/tokenizer.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/tokenizer.model
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/tokenizer_config.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -126,11 +126,251 @@
|
|
126 |
"learning_rate": 0.0003,
|
127 |
"loss": 4.9139,
|
128 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
129 |
}
|
130 |
],
|
131 |
"max_steps": 3000,
|
132 |
"num_train_epochs": 9223372036854775807,
|
133 |
-
"total_flos":
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2,
|
5 |
+
"global_step": 600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
126 |
"learning_rate": 0.0003,
|
127 |
"loss": 4.9139,
|
128 |
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.07,
|
132 |
+
"learning_rate": 0.0003,
|
133 |
+
"loss": 4.8974,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.07,
|
138 |
+
"learning_rate": 0.0003,
|
139 |
+
"loss": 4.9036,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.08,
|
144 |
+
"learning_rate": 0.0003,
|
145 |
+
"loss": 4.8635,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.08,
|
150 |
+
"learning_rate": 0.0003,
|
151 |
+
"loss": 4.7883,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.08,
|
156 |
+
"learning_rate": 0.0003,
|
157 |
+
"loss": 4.7681,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.09,
|
162 |
+
"learning_rate": 0.0003,
|
163 |
+
"loss": 4.7572,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.09,
|
168 |
+
"learning_rate": 0.0003,
|
169 |
+
"loss": 4.7552,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.09,
|
174 |
+
"learning_rate": 0.0003,
|
175 |
+
"loss": 4.706,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.1,
|
180 |
+
"learning_rate": 0.0003,
|
181 |
+
"loss": 4.7015,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.1,
|
186 |
+
"learning_rate": 0.0003,
|
187 |
+
"loss": 4.695,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.1,
|
192 |
+
"learning_rate": 0.0003,
|
193 |
+
"loss": 4.6808,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.11,
|
198 |
+
"learning_rate": 0.0003,
|
199 |
+
"loss": 4.6423,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.11,
|
204 |
+
"learning_rate": 0.0003,
|
205 |
+
"loss": 4.613,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.11,
|
210 |
+
"learning_rate": 0.0003,
|
211 |
+
"loss": 4.5851,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.12,
|
216 |
+
"learning_rate": 0.0003,
|
217 |
+
"loss": 4.5882,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.12,
|
222 |
+
"learning_rate": 0.0003,
|
223 |
+
"loss": 4.6228,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.12,
|
228 |
+
"learning_rate": 0.0003,
|
229 |
+
"loss": 4.6269,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.13,
|
234 |
+
"learning_rate": 0.0003,
|
235 |
+
"loss": 4.5364,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.13,
|
240 |
+
"learning_rate": 0.0003,
|
241 |
+
"loss": 4.4992,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.13,
|
246 |
+
"learning_rate": 0.0003,
|
247 |
+
"loss": 4.4799,
|
248 |
+
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.14,
|
252 |
+
"learning_rate": 0.0003,
|
253 |
+
"loss": 4.3733,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.14,
|
258 |
+
"learning_rate": 0.0003,
|
259 |
+
"loss": 4.1788,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.14,
|
264 |
+
"learning_rate": 0.0003,
|
265 |
+
"loss": 3.6706,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.15,
|
270 |
+
"learning_rate": 0.0003,
|
271 |
+
"loss": 2.8767,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.15,
|
276 |
+
"learning_rate": 0.0003,
|
277 |
+
"loss": 2.3927,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.15,
|
282 |
+
"learning_rate": 0.0003,
|
283 |
+
"loss": 2.3062,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.16,
|
288 |
+
"learning_rate": 0.0003,
|
289 |
+
"loss": 2.2299,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.16,
|
294 |
+
"learning_rate": 0.0003,
|
295 |
+
"loss": 2.1739,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.16,
|
300 |
+
"learning_rate": 0.0003,
|
301 |
+
"loss": 2.1303,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.17,
|
306 |
+
"learning_rate": 0.0003,
|
307 |
+
"loss": 2.1092,
|
308 |
+
"step": 500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.17,
|
312 |
+
"learning_rate": 0.0003,
|
313 |
+
"loss": 2.0715,
|
314 |
+
"step": 510
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.17,
|
318 |
+
"learning_rate": 0.0003,
|
319 |
+
"loss": 2.0473,
|
320 |
+
"step": 520
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.18,
|
324 |
+
"learning_rate": 0.0003,
|
325 |
+
"loss": 2.0566,
|
326 |
+
"step": 530
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.18,
|
330 |
+
"learning_rate": 0.0003,
|
331 |
+
"loss": 1.9818,
|
332 |
+
"step": 540
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.18,
|
336 |
+
"learning_rate": 0.0003,
|
337 |
+
"loss": 1.9592,
|
338 |
+
"step": 550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.19,
|
342 |
+
"learning_rate": 0.0003,
|
343 |
+
"loss": 1.8939,
|
344 |
+
"step": 560
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.19,
|
348 |
+
"learning_rate": 0.0003,
|
349 |
+
"loss": 1.8441,
|
350 |
+
"step": 570
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.19,
|
354 |
+
"learning_rate": 0.0003,
|
355 |
+
"loss": 1.808,
|
356 |
+
"step": 580
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.2,
|
360 |
+
"learning_rate": 0.0003,
|
361 |
+
"loss": 1.765,
|
362 |
+
"step": 590
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.2,
|
366 |
+
"learning_rate": 0.0003,
|
367 |
+
"loss": 1.706,
|
368 |
+
"step": 600
|
369 |
}
|
370 |
],
|
371 |
"max_steps": 3000,
|
372 |
"num_train_epochs": 9223372036854775807,
|
373 |
+
"total_flos": 251255586816000.0,
|
374 |
"trial_name": null,
|
375 |
"trial_params": null
|
376 |
}
|
{checkpoint-200 β checkpoint-600}/training_args.bin
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-600}/zero_to_fp32.py
RENAMED
File without changes
|
runs/Aug22_18-42-03_ip-26-0-150-12/events.out.tfevents.1692729850.ip-26-0-150-12.2895584.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:accaaa15e2b69671590fc720552ed7a07108f7a4bcf6148faf4fd30c13b18e22
|
3 |
+
size 13571
|