MohamedAhmedAE
commited on
Commit
•
be60643
1
Parent(s):
b9b15d6
Training in progress, step 3000, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0b17e3cc5361a6fb95a762276cf91289aa13131a8fbd9766fc3a4c840df560a
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d0d3e162d54962a24152dbd5b6c2d74f4ab4f1cdf06ddc47eddf9d8b6d07ca2
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c3c8b2c540004b798ef14a7898f64a9814643e8791bc9d21b3f9eb260faee38
|
3 |
size 14244
|
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:b791cefec27286739c8a8bdafe733eef68db8d09837c7ad1df5edca79390d24b
|
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": 0.
|
5 |
"eval_steps": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -105,6 +105,13 @@
|
|
105 |
"learning_rate": 1.999999149640793e-05,
|
106 |
"loss": 1.6118,
|
107 |
"step": 2800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 200,
|
@@ -112,7 +119,7 @@
|
|
112 |
"num_input_tokens_seen": 0,
|
113 |
"num_train_epochs": 5,
|
114 |
"save_steps": 200,
|
115 |
-
"total_flos": 3.
|
116 |
"train_batch_size": 1,
|
117 |
"trial_name": null,
|
118 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0022309891834207756,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 3000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
105 |
"learning_rate": 1.999999149640793e-05,
|
106 |
"loss": 1.6118,
|
107 |
"step": 2800
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.0,
|
111 |
+
"grad_norm": 3.5887880325317383,
|
112 |
+
"learning_rate": 1.9999990234026036e-05,
|
113 |
+
"loss": 1.586,
|
114 |
+
"step": 3000
|
115 |
}
|
116 |
],
|
117 |
"logging_steps": 200,
|
|
|
119 |
"num_input_tokens_seen": 0,
|
120 |
"num_train_epochs": 5,
|
121 |
"save_steps": 200,
|
122 |
+
"total_flos": 3.905599131493171e+16,
|
123 |
"train_batch_size": 1,
|
124 |
"trial_name": null,
|
125 |
"trial_params": null
|