lesso commited on
Commit
4ff396f
1 Parent(s): 424c5fe

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "down_proj",
24
- "k_proj",
25
- "q_proj",
26
  "gate_proj",
 
27
  "v_proj",
28
- "o_proj",
29
- "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "o_proj",
24
+ "up_proj",
 
25
  "gate_proj",
26
+ "k_proj",
27
  "v_proj",
28
+ "q_proj",
29
+ "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf12e03f6739bc0f7a478e3a172c01dd5f398c4bbb99b6b05cae950ea51679d4
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea908fe7a6a05e827cb4a10ef12cff2edb8dae4c7310af8a09db48c810565e8
3
  size 25271744
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5364d09e27bdf541cc4080b011a0a833388b061da2ef703197275a4e77a4aa4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4032206871f76f267774b23b5210fddd18559968f207e84376a2a9e45c5846
3
  size 14244
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.006683375104427736,
5
  "eval_steps": 3,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -18,9 +18,9 @@
18
  {
19
  "epoch": 0.0006683375104427736,
20
  "eval_loss": 6.567427635192871,
21
- "eval_runtime": 10.2795,
22
- "eval_samples_per_second": 30.741,
23
- "eval_steps_per_second": 30.741,
24
  "step": 1
25
  },
26
  {
@@ -40,9 +40,9 @@
40
  {
41
  "epoch": 0.0020050125313283208,
42
  "eval_loss": 6.567427635192871,
43
- "eval_runtime": 10.2668,
44
- "eval_samples_per_second": 30.779,
45
- "eval_steps_per_second": 30.779,
46
  "step": 3
47
  },
48
  {
@@ -69,9 +69,9 @@
69
  {
70
  "epoch": 0.0040100250626566416,
71
  "eval_loss": 6.567427635192871,
72
- "eval_runtime": 10.6828,
73
- "eval_samples_per_second": 29.58,
74
- "eval_steps_per_second": 29.58,
75
  "step": 6
76
  },
77
  {
@@ -98,17 +98,10 @@
98
  {
99
  "epoch": 0.006015037593984963,
100
  "eval_loss": 6.567427635192871,
101
- "eval_runtime": 10.3575,
102
- "eval_samples_per_second": 30.509,
103
- "eval_steps_per_second": 30.509,
104
  "step": 9
105
- },
106
- {
107
- "epoch": 0.006683375104427736,
108
- "grad_norm": NaN,
109
- "learning_rate": 0.0,
110
- "loss": 6.3319,
111
- "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
@@ -123,12 +116,12 @@
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
- "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
- "total_flos": 255791978250240.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006015037593984963,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
18
  {
19
  "epoch": 0.0006683375104427736,
20
  "eval_loss": 6.567427635192871,
21
+ "eval_runtime": 12.5721,
22
+ "eval_samples_per_second": 25.135,
23
+ "eval_steps_per_second": 25.135,
24
  "step": 1
25
  },
26
  {
 
40
  {
41
  "epoch": 0.0020050125313283208,
42
  "eval_loss": 6.567427635192871,
43
+ "eval_runtime": 12.4056,
44
+ "eval_samples_per_second": 25.472,
45
+ "eval_steps_per_second": 25.472,
46
  "step": 3
47
  },
48
  {
 
69
  {
70
  "epoch": 0.0040100250626566416,
71
  "eval_loss": 6.567427635192871,
72
+ "eval_runtime": 12.9457,
73
+ "eval_samples_per_second": 24.41,
74
+ "eval_steps_per_second": 24.41,
75
  "step": 6
76
  },
77
  {
 
98
  {
99
  "epoch": 0.006015037593984963,
100
  "eval_loss": 6.567427635192871,
101
+ "eval_runtime": 12.5182,
102
+ "eval_samples_per_second": 25.243,
103
+ "eval_steps_per_second": 25.243,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
 
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
+ "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 230212780425216.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bf7f2cad6e11c0ce3e3076a28f4690cfb1e863a19192d0c9a93217476d185e7
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33c14880d19facfd321016a9bcfbb3088b8c60b69f0d839be31c2284ef19082
3
  size 6776