Training in progress, step 15, 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 +25 -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 247944
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55ddef84a5d51bfa291e0a1231780d7f7e8c0e3d93c9b3834e04fc8a0eaa62d9
|
3 |
size 247944
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 263024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97250f7f398a115affe0f6618dbc679b0f98fa5f87cc126801be83fdabe2ab59
|
3 |
size 263024
|
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 sha256:91690f13f8da196ad046ee2c4253c58f98a8be6238b84a3c00a87418d505f9a1
|
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 sha256:444255f105350f0c41364e580c5fd405b82b9cd4bd5a09beeb18720eefd30bfb
|
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 sha256:16a60bdd2de3f82fc9413541acb6ca5108a914a84ae0c18f4388999fab955ce8
|
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 sha256:0e40eb4a102d15fb57568ab9cabb695b9acc547d984a6f742fe0285988b9b4a2
|
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:d79d00677fa831f97f3cce7f98a08b9f551f8585dcf67b430bb2253437cabb70
|
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:f7edd6c308e044c55d4572cb66320998dfdd3cf8c48260ee2675566442b17b64
|
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 sha256:8ea0b1e6a530277e934b09b6ea702568d7a5bf363cff457cc29f8f7ec04ec064
|
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 sha256:1b2a85b2a9a7aa63e96969424e273f3c52cc0d01037fa783fcba44c167579370
|
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 sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
|
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": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -123,6 +123,27 @@
|
|
123 |
"eval_samples_per_second": 905.76,
|
124 |
"eval_steps_per_second": 121.391,
|
125 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
126 |
}
|
127 |
],
|
128 |
"logging_steps": 1,
|
@@ -137,12 +158,12 @@
|
|
137 |
"should_evaluate": false,
|
138 |
"should_log": false,
|
139 |
"should_save": true,
|
140 |
-
"should_training_stop":
|
141 |
},
|
142 |
"attributes": {}
|
143 |
}
|
144 |
},
|
145 |
-
"total_flos":
|
146 |
"train_batch_size": 1,
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0434782608695652,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
123 |
"eval_samples_per_second": 905.76,
|
124 |
"eval_steps_per_second": 121.391,
|
125 |
"step": 12
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.9043478260869565,
|
129 |
+
"grad_norm": 8.3920259475708,
|
130 |
+
"learning_rate": 3.4549150281252636e-05,
|
131 |
+
"loss": 176.8594,
|
132 |
+
"step": 13
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 0.9739130434782609,
|
136 |
+
"grad_norm": 8.231620788574219,
|
137 |
+
"learning_rate": 9.549150281252633e-06,
|
138 |
+
"loss": 176.8672,
|
139 |
+
"step": 14
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 1.0434782608695652,
|
143 |
+
"grad_norm": 8.611029624938965,
|
144 |
+
"learning_rate": 0.0,
|
145 |
+
"loss": 176.7188,
|
146 |
+
"step": 15
|
147 |
}
|
148 |
],
|
149 |
"logging_steps": 1,
|
|
|
158 |
"should_evaluate": false,
|
159 |
"should_log": false,
|
160 |
"should_save": true,
|
161 |
+
"should_training_stop": true
|
162 |
},
|
163 |
"attributes": {}
|
164 |
}
|
165 |
},
|
166 |
+
"total_flos": 19967571394560.0,
|
167 |
"train_batch_size": 1,
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|