Training in progress, step 2000, checkpoint
Browse files- last-checkpoint/adapter_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 +19 -4
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627606952
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8b4c290a0473e3f1a83750a409562d823c6df4a1b7a59e78e869dd7ad4ff004
|
3 |
size 627606952
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 318985924
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:757014c53f19b73e429af204a5338d3f14676b7fc2c7966ce939c733cec084fc
|
3 |
size 318985924
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b579740f0f439f469c486c69eea58de2c5120d23d26733b64db7c7667df71a90
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f58d40a7f8af25cfc5622dc7ce8236177ec2ab2d63460c9947df6c8985225e32
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f7c278c6bb8d46d099e72f39e89da9bd3a2bc727a0e97053dcb3adc0e3887f4
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:624bc06ceaa4f535ee5bd5523aba308ae079239fd1216a542ff7f206dfe9e0d6
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5846dae2a3f5d45e9c6a0d8735dbdf59f88cd724bb5390de8d74fdb0a3570143
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fd362c0cdd2c0b07695c69ba21a13f79c1271c6cc1f095f8c8f3826affb6f2d
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfadb0579f7e6f5845d871b6bdfc6bac7aa6c9d1a062b11d56ebfd5eb6cb6f5f
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:665b232df28dd286682f25be6672af0fa77ccef4cdff53c9e9e9243286f09d8b
|
3 |
size 15984
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff620fa731932bfad032c9b2869fcd08718601bc76c1b44cf37971591fc72fbd
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -2200,6 +2200,21 @@
|
|
2200 |
"learning_rate": 1.2486132855826781e-08,
|
2201 |
"loss": 0.0002,
|
2202 |
"step": 1990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2203 |
}
|
2204 |
],
|
2205 |
"logging_steps": 10,
|
@@ -2214,12 +2229,12 @@
|
|
2214 |
"should_evaluate": false,
|
2215 |
"should_log": false,
|
2216 |
"should_save": true,
|
2217 |
-
"should_training_stop":
|
2218 |
},
|
2219 |
"attributes": {}
|
2220 |
}
|
2221 |
},
|
2222 |
-
"total_flos": 4.
|
2223 |
"train_batch_size": 1,
|
2224 |
"trial_name": null,
|
2225 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2200 |
"learning_rate": 1.2486132855826781e-08,
|
2201 |
"loss": 0.0002,
|
2202 |
"step": 1990
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 100.0,
|
2206 |
+
"grad_norm": 0.0007593940244987607,
|
2207 |
+
"learning_rate": 0.0,
|
2208 |
+
"loss": 0.0002,
|
2209 |
+
"step": 2000
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 100.0,
|
2213 |
+
"eval_loss": 1.9426655769348145,
|
2214 |
+
"eval_runtime": 0.396,
|
2215 |
+
"eval_samples_per_second": 45.452,
|
2216 |
+
"eval_steps_per_second": 7.575,
|
2217 |
+
"step": 2000
|
2218 |
}
|
2219 |
],
|
2220 |
"logging_steps": 10,
|
|
|
2229 |
"should_evaluate": false,
|
2230 |
"should_log": false,
|
2231 |
"should_save": true,
|
2232 |
+
"should_training_stop": true
|
2233 |
},
|
2234 |
"attributes": {}
|
2235 |
}
|
2236 |
},
|
2237 |
+
"total_flos": 4.205007863808e+17,
|
2238 |
"train_batch_size": 1,
|
2239 |
"trial_name": null,
|
2240 |
"trial_params": null
|