Training in progress, step 11721, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +18 -4
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 735396724
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abce02565756a58f46b692b6631ce962a5d8d0a280f132430d995a674310b6a3
|
| 3 |
size 735396724
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470915147
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc0ad490257e5aa529e403354667f6f46b1f752d8ca988323a95135f3ac07cfd
|
| 3 |
size 1470915147
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61784067eeeddbc6007986a60807ca952c479a5d616edd743fce6d61fb060b81
|
| 3 |
size 16325
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:403fde2aa094db2523f0f8767a1aad70807a06830fadcc84399fb47044834af0
|
| 3 |
size 16325
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:302e27b15416035b52cee0060a75a1594ba8db740cbc61d1b5f5381d8c44359e
|
| 3 |
size 16325
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b27ea9877e292e797a620756b641c321e75bc42290903e1a4599c9bcf4cb0ec
|
| 3 |
size 16325
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:568eadcfbd9e3a1cd4c988467bf35f9ff35c7a3830ea675e5bd2fc3a9bb4d061
|
| 3 |
size 16325
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:583278ccc1efa64baf9b41eacf5d3167d993e3034b88663832af101c52c2f4d5
|
| 3 |
size 16325
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ac7a0339dbd160bbd940be8682e9433de6f3f50495257cc674f3c9131064ea
|
| 3 |
size 16325
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09993e634468aeb991d96caead9c550e8064ebeb6585b8e3b5ff1df55dc1a632
|
| 3 |
size 16325
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17e75b8fcae7f67d45916b291faac93526454fac16b6d7113017dd3227b05ba4
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 9800,
|
| 3 |
"best_metric": 0.7528361702207996,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-9800",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 200,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2270,6 +2270,20 @@
|
|
| 2270 |
"eval_samples_per_second": 1679.412,
|
| 2271 |
"eval_steps_per_second": 26.241,
|
| 2272 |
"step": 11600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2273 |
}
|
| 2274 |
],
|
| 2275 |
"logging_steps": 50,
|
|
@@ -2284,12 +2298,12 @@
|
|
| 2284 |
"should_evaluate": false,
|
| 2285 |
"should_log": false,
|
| 2286 |
"should_save": true,
|
| 2287 |
-
"should_training_stop":
|
| 2288 |
},
|
| 2289 |
"attributes": {}
|
| 2290 |
}
|
| 2291 |
},
|
| 2292 |
-
"total_flos": 1.
|
| 2293 |
"train_batch_size": 256,
|
| 2294 |
"trial_name": null,
|
| 2295 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 9800,
|
| 3 |
"best_metric": 0.7528361702207996,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-9800",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
"eval_steps": 200,
|
| 7 |
+
"global_step": 11721,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2270 |
"eval_samples_per_second": 1679.412,
|
| 2271 |
"eval_steps_per_second": 26.241,
|
| 2272 |
"step": 11600
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 2.9818274891220886,
|
| 2276 |
+
"grad_norm": 0.20488199591636658,
|
| 2277 |
+
"learning_rate": 2.4739213958790976e-09,
|
| 2278 |
+
"loss": 0.0769,
|
| 2279 |
+
"step": 11650
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 2.9946250319938574,
|
| 2283 |
+
"grad_norm": 0.2265998274087906,
|
| 2284 |
+
"learning_rate": 2.3098259378240282e-10,
|
| 2285 |
+
"loss": 0.0797,
|
| 2286 |
+
"step": 11700
|
| 2287 |
}
|
| 2288 |
],
|
| 2289 |
"logging_steps": 50,
|
|
|
|
| 2298 |
"should_evaluate": false,
|
| 2299 |
"should_log": false,
|
| 2300 |
"should_save": true,
|
| 2301 |
+
"should_training_stop": true
|
| 2302 |
},
|
| 2303 |
"attributes": {}
|
| 2304 |
}
|
| 2305 |
},
|
| 2306 |
+
"total_flos": 1.482524685198426e+18,
|
| 2307 |
"train_batch_size": 256,
|
| 2308 |
"trial_name": null,
|
| 2309 |
"trial_params": null
|