MohamedAhmedAE
commited on
Commit
•
e9e98a9
1
Parent(s):
3c3a946
Training in progress, step 2600, 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:ee35ec5705f2b811f92a9e6d3e8abd9d7841a06e0b1cdb058d0636a938521326
|
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:a92847cc760dd26eff17b8a1e591ef8a11654bbf43764bb1bd3c3d2398a270b4
|
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 sha256:7ffda2d0a868091a3ca3379a2e5ec9b477c1a5e302eb3cf2177106a9488251e8
|
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 sha256:12050bdf0b8719c103ea937805d9f70f4d557382cbab2e264e9fd8308c1c5527
|
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,
|
@@ -91,6 +91,13 @@
|
|
91 |
"learning_rate": 1.9999993759176304e-05,
|
92 |
"loss": 1.564,
|
93 |
"step": 2400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 200,
|
@@ -98,7 +105,7 @@
|
|
98 |
"num_input_tokens_seen": 0,
|
99 |
"num_train_epochs": 5,
|
100 |
"save_steps": 200,
|
101 |
-
"total_flos": 3.
|
102 |
"train_batch_size": 1,
|
103 |
"trial_name": null,
|
104 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0019335239589646724,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 2600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
91 |
"learning_rate": 1.9999993759176304e-05,
|
92 |
"loss": 1.564,
|
93 |
"step": 2400
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.0,
|
97 |
+
"grad_norm": 1.8213422298431396,
|
98 |
+
"learning_rate": 1.9999992671458023e-05,
|
99 |
+
"loss": 1.5586,
|
100 |
+
"step": 2600
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 200,
|
|
|
105 |
"num_input_tokens_seen": 0,
|
106 |
"num_train_epochs": 5,
|
107 |
"save_steps": 200,
|
108 |
+
"total_flos": 3.3719238906126336e+16,
|
109 |
"train_batch_size": 1,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|