Upload folder using huggingface_hub
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- checkpoint-100/adapter_config.json +3 -3
- checkpoint-100/adapter_model.safetensors +1 -1
- checkpoint-100/optimizer.pt +1 -1
- checkpoint-100/trainer_state.json +20 -20
- checkpoint-100/training_args.bin +1 -1
- checkpoint-200/adapter_config.json +3 -3
- checkpoint-200/adapter_model.safetensors +1 -1
- checkpoint-200/optimizer.pt +1 -1
- checkpoint-200/trainer_state.json +39 -39
- checkpoint-200/training_args.bin +1 -1
- runs/Nov25_04-13-55_fa8d08851cd4/events.out.tfevents.1732508036.fa8d08851cd4.17420.0 +3 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -21,12 +21,12 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"up_proj",
|
| 24 |
-
"o_proj",
|
| 25 |
-
"down_proj",
|
| 26 |
"k_proj",
|
|
|
|
| 27 |
"q_proj",
|
|
|
|
| 28 |
"v_proj",
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"up_proj",
|
|
|
|
|
|
|
| 24 |
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
"q_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
"v_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 39256456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:446b7bc018c5325fe2f65edba45a90184b0b9dcd2790d2a11547c257ebf891e3
|
| 3 |
size 39256456
|
checkpoint-100/adapter_config.json
CHANGED
|
@@ -21,12 +21,12 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"up_proj",
|
| 24 |
-
"o_proj",
|
| 25 |
-
"down_proj",
|
| 26 |
"k_proj",
|
|
|
|
| 27 |
"q_proj",
|
|
|
|
| 28 |
"v_proj",
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"up_proj",
|
|
|
|
|
|
|
| 24 |
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
"q_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
"v_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
checkpoint-100/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 39256456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f51c614f56ddd64b5615445f23c73ac6181027a5eef12e2765f4eff803a4926
|
| 3 |
size 39256456
|
checkpoint-100/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 20635834
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b1f8ce6e76d5cf076a3c3291bc596d7ad36fc5f2ed9ecb6f072bb890caf4ca8
|
| 3 |
size 20635834
|
checkpoint-100/trainer_state.json
CHANGED
|
@@ -10,72 +10,72 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03988035892323031,
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
-
"loss": 3.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.07976071784646062,
|
| 20 |
-
"grad_norm": 3.
|
| 21 |
"learning_rate": 0.00019863613034027224,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.11964107676969092,
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
"learning_rate": 0.00019458172417006347,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.15952143569292124,
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
"learning_rate": 0.0001879473751206489,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.19940179461615154,
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
"learning_rate": 0.00017891405093963938,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.23928215353938184,
|
| 48 |
-
"grad_norm": 1.
|
| 49 |
"learning_rate": 0.00016772815716257412,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.27916251246261214,
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
"learning_rate": 0.00015469481581224272,
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.3190428713858425,
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
"learning_rate": 0.00014016954246529696,
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.3589232303090728,
|
| 69 |
-
"grad_norm": 1.
|
| 70 |
"learning_rate": 0.00012454854871407994,
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3988035892323031,
|
| 76 |
-
"grad_norm":
|
| 77 |
"learning_rate": 0.00010825793454723325,
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
}
|
| 81 |
],
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03988035892323031,
|
| 13 |
+
"grad_norm": 13.419048309326172,
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 3.2212,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.07976071784646062,
|
| 20 |
+
"grad_norm": 3.605897903442383,
|
| 21 |
"learning_rate": 0.00019863613034027224,
|
| 22 |
+
"loss": 0.9339,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.11964107676969092,
|
| 27 |
+
"grad_norm": 1.9724041223526,
|
| 28 |
"learning_rate": 0.00019458172417006347,
|
| 29 |
+
"loss": 0.4623,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.15952143569292124,
|
| 34 |
+
"grad_norm": 1.7109146118164062,
|
| 35 |
"learning_rate": 0.0001879473751206489,
|
| 36 |
+
"loss": 0.3536,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.19940179461615154,
|
| 41 |
+
"grad_norm": 0.9077266454696655,
|
| 42 |
"learning_rate": 0.00017891405093963938,
|
| 43 |
+
"loss": 0.3476,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.23928215353938184,
|
| 48 |
+
"grad_norm": 1.310617446899414,
|
| 49 |
"learning_rate": 0.00016772815716257412,
|
| 50 |
+
"loss": 0.3369,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.27916251246261214,
|
| 55 |
+
"grad_norm": 0.8259612321853638,
|
| 56 |
"learning_rate": 0.00015469481581224272,
|
| 57 |
+
"loss": 0.3062,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.3190428713858425,
|
| 62 |
+
"grad_norm": 1.113377571105957,
|
| 63 |
"learning_rate": 0.00014016954246529696,
|
| 64 |
+
"loss": 0.2959,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.3589232303090728,
|
| 69 |
+
"grad_norm": 1.0124801397323608,
|
| 70 |
"learning_rate": 0.00012454854871407994,
|
| 71 |
+
"loss": 0.3015,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3988035892323031,
|
| 76 |
+
"grad_norm": 2.501101016998291,
|
| 77 |
"learning_rate": 0.00010825793454723325,
|
| 78 |
+
"loss": 0.31,
|
| 79 |
"step": 100
|
| 80 |
}
|
| 81 |
],
|
checkpoint-100/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdf0ef5a9df3c94b8e9a929302c79114e13ffa4c53b39022c4b0704a368ac5c0
|
| 3 |
size 5304
|
checkpoint-200/adapter_config.json
CHANGED
|
@@ -21,12 +21,12 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"up_proj",
|
| 24 |
-
"o_proj",
|
| 25 |
-
"down_proj",
|
| 26 |
"k_proj",
|
|
|
|
| 27 |
"q_proj",
|
|
|
|
| 28 |
"v_proj",
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"up_proj",
|
|
|
|
|
|
|
| 24 |
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
"q_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
"v_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
checkpoint-200/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 39256456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:446b7bc018c5325fe2f65edba45a90184b0b9dcd2790d2a11547c257ebf891e3
|
| 3 |
size 39256456
|
checkpoint-200/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 20635834
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:188d58e74e4fb328b053f4e2f4b75fa6e0b79127978b21b899ee5966645ee32c
|
| 3 |
size 20635834
|
checkpoint-200/trainer_state.json
CHANGED
|
@@ -10,142 +10,142 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03988035892323031,
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
-
"loss": 3.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.07976071784646062,
|
| 20 |
-
"grad_norm": 3.
|
| 21 |
"learning_rate": 0.00019863613034027224,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.11964107676969092,
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
"learning_rate": 0.00019458172417006347,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.15952143569292124,
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
"learning_rate": 0.0001879473751206489,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.19940179461615154,
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
"learning_rate": 0.00017891405093963938,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.23928215353938184,
|
| 48 |
-
"grad_norm": 1.
|
| 49 |
"learning_rate": 0.00016772815716257412,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.27916251246261214,
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
"learning_rate": 0.00015469481581224272,
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.3190428713858425,
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
"learning_rate": 0.00014016954246529696,
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.3589232303090728,
|
| 69 |
-
"grad_norm": 1.
|
| 70 |
"learning_rate": 0.00012454854871407994,
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3988035892323031,
|
| 76 |
-
"grad_norm":
|
| 77 |
"learning_rate": 0.00010825793454723325,
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.4386839481555334,
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
"learning_rate": 9.174206545276677e-05,
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.4785643070787637,
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
"learning_rate": 7.54514512859201e-05,
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.518444666001994,
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
"learning_rate": 5.983045753470308e-05,
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.5583250249252243,
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
"learning_rate": 4.530518418775733e-05,
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.5982053838484547,
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
"learning_rate": 3.227184283742591e-05,
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.638085742771685,
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
"learning_rate": 2.1085949060360654e-05,
|
| 120 |
"loss": 0.2453,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.6779661016949152,
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
"learning_rate": 1.2052624879351104e-05,
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.7178464606181456,
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
"learning_rate": 5.418275829936537e-06,
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.7577268195413759,
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
"learning_rate": 1.3638696597277679e-06,
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.7976071784646062,
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
"learning_rate": 0.0,
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 200
|
| 150 |
}
|
| 151 |
],
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03988035892323031,
|
| 13 |
+
"grad_norm": 13.419048309326172,
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 3.2212,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.07976071784646062,
|
| 20 |
+
"grad_norm": 3.605897903442383,
|
| 21 |
"learning_rate": 0.00019863613034027224,
|
| 22 |
+
"loss": 0.9339,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.11964107676969092,
|
| 27 |
+
"grad_norm": 1.9724041223526,
|
| 28 |
"learning_rate": 0.00019458172417006347,
|
| 29 |
+
"loss": 0.4623,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.15952143569292124,
|
| 34 |
+
"grad_norm": 1.7109146118164062,
|
| 35 |
"learning_rate": 0.0001879473751206489,
|
| 36 |
+
"loss": 0.3536,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.19940179461615154,
|
| 41 |
+
"grad_norm": 0.9077266454696655,
|
| 42 |
"learning_rate": 0.00017891405093963938,
|
| 43 |
+
"loss": 0.3476,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.23928215353938184,
|
| 48 |
+
"grad_norm": 1.310617446899414,
|
| 49 |
"learning_rate": 0.00016772815716257412,
|
| 50 |
+
"loss": 0.3369,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.27916251246261214,
|
| 55 |
+
"grad_norm": 0.8259612321853638,
|
| 56 |
"learning_rate": 0.00015469481581224272,
|
| 57 |
+
"loss": 0.3062,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.3190428713858425,
|
| 62 |
+
"grad_norm": 1.113377571105957,
|
| 63 |
"learning_rate": 0.00014016954246529696,
|
| 64 |
+
"loss": 0.2959,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.3589232303090728,
|
| 69 |
+
"grad_norm": 1.0124801397323608,
|
| 70 |
"learning_rate": 0.00012454854871407994,
|
| 71 |
+
"loss": 0.3015,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3988035892323031,
|
| 76 |
+
"grad_norm": 2.501101016998291,
|
| 77 |
"learning_rate": 0.00010825793454723325,
|
| 78 |
+
"loss": 0.31,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.4386839481555334,
|
| 83 |
+
"grad_norm": 0.782170832157135,
|
| 84 |
"learning_rate": 9.174206545276677e-05,
|
| 85 |
+
"loss": 0.2866,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.4785643070787637,
|
| 90 |
+
"grad_norm": 0.9728937745094299,
|
| 91 |
"learning_rate": 7.54514512859201e-05,
|
| 92 |
+
"loss": 0.2685,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.518444666001994,
|
| 97 |
+
"grad_norm": 0.9312043190002441,
|
| 98 |
"learning_rate": 5.983045753470308e-05,
|
| 99 |
+
"loss": 0.2708,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.5583250249252243,
|
| 104 |
+
"grad_norm": 0.8518964648246765,
|
| 105 |
"learning_rate": 4.530518418775733e-05,
|
| 106 |
+
"loss": 0.2512,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.5982053838484547,
|
| 111 |
+
"grad_norm": 0.6809622645378113,
|
| 112 |
"learning_rate": 3.227184283742591e-05,
|
| 113 |
+
"loss": 0.2421,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.638085742771685,
|
| 118 |
+
"grad_norm": 0.7239226698875427,
|
| 119 |
"learning_rate": 2.1085949060360654e-05,
|
| 120 |
"loss": 0.2453,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.6779661016949152,
|
| 125 |
+
"grad_norm": 0.7479511499404907,
|
| 126 |
"learning_rate": 1.2052624879351104e-05,
|
| 127 |
+
"loss": 0.2636,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.7178464606181456,
|
| 132 |
+
"grad_norm": 0.9504374861717224,
|
| 133 |
"learning_rate": 5.418275829936537e-06,
|
| 134 |
+
"loss": 0.2658,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.7577268195413759,
|
| 139 |
+
"grad_norm": 0.7279093861579895,
|
| 140 |
"learning_rate": 1.3638696597277679e-06,
|
| 141 |
+
"loss": 0.2461,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.7976071784646062,
|
| 146 |
+
"grad_norm": 0.9317768216133118,
|
| 147 |
"learning_rate": 0.0,
|
| 148 |
+
"loss": 0.2577,
|
| 149 |
"step": 200
|
| 150 |
}
|
| 151 |
],
|
checkpoint-200/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdf0ef5a9df3c94b8e9a929302c79114e13ffa4c53b39022c4b0704a368ac5c0
|
| 3 |
size 5304
|
runs/Nov25_04-13-55_fa8d08851cd4/events.out.tfevents.1732508036.fa8d08851cd4.17420.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94dc0d4583f22f43b1b2d9d35a266f2a36fdf3549981fb4c44b3afc7a2dcbcc9
|
| 3 |
+
size 10163
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdf0ef5a9df3c94b8e9a929302c79114e13ffa4c53b39022c4b0704a368ac5c0
|
| 3 |
size 5304
|