Training in progress, step 1380, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1316913776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e6fd9f618893f644cfadd4228ceb3e59f5cd108b7cc283289927b01ea5dc154
|
| 3 |
size 1316913776
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8908124
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8f4f2515e6d3b23f0ca6faca87ae230002ea69d7ab00be35f2798b878d9bcde
|
| 3 |
size 8908124
|
last-checkpoint/rng_state.pth
CHANGED
|
Binary files a/last-checkpoint/rng_state.pth and b/last-checkpoint/rng_state.pth differ
|
|
|
last-checkpoint/scheduler.pt
CHANGED
|
Binary files a/last-checkpoint/scheduler.pt and b/last-checkpoint/scheduler.pt differ
|
|
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -952,6 +952,27 @@
|
|
| 952 |
"learning_rate": 0.00035508802060970376,
|
| 953 |
"loss": 0.7831,
|
| 954 |
"step": 1350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 955 |
}
|
| 956 |
],
|
| 957 |
"logging_steps": 10,
|
|
@@ -959,7 +980,7 @@
|
|
| 959 |
"num_input_tokens_seen": 0,
|
| 960 |
"num_train_epochs": 1,
|
| 961 |
"save_steps": 10,
|
| 962 |
-
"total_flos": 1.
|
| 963 |
"train_batch_size": 3,
|
| 964 |
"trial_name": null,
|
| 965 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.296264491197939,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1380,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 952 |
"learning_rate": 0.00035508802060970376,
|
| 953 |
"loss": 0.7831,
|
| 954 |
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.291970802919708,
|
| 958 |
+
"grad_norm": 1.1971302032470703,
|
| 959 |
+
"learning_rate": 0.000354014598540146,
|
| 960 |
+
"loss": 0.7673,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.29411764705882354,
|
| 965 |
+
"grad_norm": 1.3551030158996582,
|
| 966 |
+
"learning_rate": 0.00035294117647058826,
|
| 967 |
+
"loss": 0.7757,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.296264491197939,
|
| 972 |
+
"grad_norm": 1.0632190704345703,
|
| 973 |
+
"learning_rate": 0.0003518677544010305,
|
| 974 |
+
"loss": 0.7824,
|
| 975 |
+
"step": 1380
|
| 976 |
}
|
| 977 |
],
|
| 978 |
"logging_steps": 10,
|
|
|
|
| 980 |
"num_input_tokens_seen": 0,
|
| 981 |
"num_train_epochs": 1,
|
| 982 |
"save_steps": 10,
|
| 983 |
+
"total_flos": 1.0474038096936192e+17,
|
| 984 |
"train_batch_size": 3,
|
| 985 |
"trial_name": null,
|
| 986 |
"trial_params": null
|