Training in progress, step 600, 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 25191576
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15d235dd4f22474b64df8ce0ef64563bab763eee65a3610334d7384324c6d428
|
3 |
size 25191576
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50444805
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c1e3a91f081758f88234877225e82773ade292679f0d00129a5a4dddcdd21c3
|
3 |
size 50444805
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:736aa12ab6d5c2752499f4b6cc92b34030f49fdd84c8300d2601eb487bc8024a
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -77,6 +77,20 @@
|
|
77 |
"eval_samples_per_second": 5.474,
|
78 |
"eval_steps_per_second": 0.686,
|
79 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 100,
|
@@ -84,7 +98,7 @@
|
|
84 |
"num_input_tokens_seen": 0,
|
85 |
"num_train_epochs": 3,
|
86 |
"save_steps": 100,
|
87 |
-
"total_flos": 1.
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
90 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0178813934326172,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-600",
|
4 |
+
"epoch": 0.8,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
77 |
"eval_samples_per_second": 5.474,
|
78 |
"eval_steps_per_second": 0.686,
|
79 |
"step": 500
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.8,
|
83 |
+
"learning_rate": 0.0002,
|
84 |
+
"loss": 0.8815,
|
85 |
+
"step": 600
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 0.8,
|
89 |
+
"eval_loss": 1.0178813934326172,
|
90 |
+
"eval_runtime": 353.5441,
|
91 |
+
"eval_samples_per_second": 5.459,
|
92 |
+
"eval_steps_per_second": 0.684,
|
93 |
+
"step": 600
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 100,
|
|
|
98 |
"num_input_tokens_seen": 0,
|
99 |
"num_train_epochs": 3,
|
100 |
"save_steps": 100,
|
101 |
+
"total_flos": 1.6961466390695117e+17,
|
102 |
"trial_name": null,
|
103 |
"trial_params": null
|
104 |
}
|