rakhman-llm
commited on
Commit
•
bc2d9e2
1
Parent(s):
08b3a27
Training in progress, step 7000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52505d06ff3ae7e7722f22aa43c3fc5b8ad96c0a537d7e9c79da9d5b152aebe2
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db28a6c36094322bfed08993c1daae55a34222efe7ece9b79aad4409b339902a
|
3 |
size 1783272762
|
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:d201843135a1eed508b1bfdef27db8413b4debdba9826e312a0df4e52244dac2
|
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:f1fe29dcca1504d02fcda85bfbd112a8c1eec19fab9dfffe8372c01fb4bcb7fd
|
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": 1.
|
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,
|
@@ -106,6 +106,13 @@
|
|
106 |
"learning_rate": 1.099889165973954e-05,
|
107 |
"loss": 0.3624,
|
108 |
"step": 6500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
}
|
110 |
],
|
111 |
"logging_steps": 500,
|
@@ -125,7 +132,7 @@
|
|
125 |
"attributes": {}
|
126 |
}
|
127 |
},
|
128 |
-
"total_flos":
|
129 |
"train_batch_size": 2,
|
130 |
"trial_name": null,
|
131 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.4546965918536992,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
106 |
"learning_rate": 1.099889165973954e-05,
|
107 |
"loss": 0.3624,
|
108 |
"step": 6500
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.4546965918536992,
|
112 |
+
"grad_norm": 0.3497615456581116,
|
113 |
+
"learning_rate": 1.0306178996952066e-05,
|
114 |
+
"loss": 0.3516,
|
115 |
+
"step": 7000
|
116 |
}
|
117 |
],
|
118 |
"logging_steps": 500,
|
|
|
132 |
"attributes": {}
|
133 |
}
|
134 |
},
|
135 |
+
"total_flos": 8524801509949440.0,
|
136 |
"train_batch_size": 2,
|
137 |
"trial_name": null,
|
138 |
"trial_params": null
|