Upload 14 files
Browse files- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +715 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"summary_type": "cls_index",
|
| 31 |
"summary_use_proj": true,
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.46.
|
| 34 |
"use_cache": true,
|
| 35 |
"vocab_size": 50001
|
| 36 |
}
|
|
|
|
| 30 |
"summary_type": "cls_index",
|
| 31 |
"summary_use_proj": true,
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.46.3",
|
| 34 |
"use_cache": true,
|
| 35 |
"vocab_size": 50001
|
| 36 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 0,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 1,
|
| 6 |
-
"transformers_version": "4.46.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 0,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.46.3"
|
| 7 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 496987776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8360d44d5ce66341561f0d021dee5e6ec8b81a9d0ac51100ec01062377c05d0
|
| 3 |
size 496987776
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a409b4c21409b3f5f3bea9fd21e0022032e9104ee78dc52fce32cd4bf8c57408
|
| 3 |
+
size 994069434
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f76bfe8f06baf38f8182595ee79f69c0e5bbee8d3bad925e5bf08c9df044d87
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9381fb001e35cd6e41636b5024ecdcb43506de9707280bc0ad45e4a9c2e3995a
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,715 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 31479,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.047650814828933574,
|
| 13 |
+
"grad_norm": 2.0100979804992676,
|
| 14 |
+
"learning_rate": 0.00019682327901140442,
|
| 15 |
+
"loss": 2.3566,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09530162965786715,
|
| 20 |
+
"grad_norm": 1.877261996269226,
|
| 21 |
+
"learning_rate": 0.00019364655802280888,
|
| 22 |
+
"loss": 2.2178,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09530162965786715,
|
| 27 |
+
"eval_loss": 2.3788223266601562,
|
| 28 |
+
"eval_runtime": 80.302,
|
| 29 |
+
"eval_samples_per_second": 173.271,
|
| 30 |
+
"eval_steps_per_second": 7.223,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.14295244448680072,
|
| 35 |
+
"grad_norm": 1.7388309240341187,
|
| 36 |
+
"learning_rate": 0.00019046983703421329,
|
| 37 |
+
"loss": 2.1744,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1906032593157343,
|
| 42 |
+
"grad_norm": 1.8366143703460693,
|
| 43 |
+
"learning_rate": 0.00018729311604561772,
|
| 44 |
+
"loss": 2.163,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1906032593157343,
|
| 49 |
+
"eval_loss": 2.3654611110687256,
|
| 50 |
+
"eval_runtime": 80.3504,
|
| 51 |
+
"eval_samples_per_second": 173.166,
|
| 52 |
+
"eval_steps_per_second": 7.218,
|
| 53 |
+
"step": 2000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.23825407414466787,
|
| 57 |
+
"grad_norm": 1.6628751754760742,
|
| 58 |
+
"learning_rate": 0.00018411639505702213,
|
| 59 |
+
"loss": 2.1515,
|
| 60 |
+
"step": 2500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.28590488897360145,
|
| 64 |
+
"grad_norm": 1.6291817426681519,
|
| 65 |
+
"learning_rate": 0.0001809396740684266,
|
| 66 |
+
"loss": 2.1196,
|
| 67 |
+
"step": 3000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.28590488897360145,
|
| 71 |
+
"eval_loss": 2.3521649837493896,
|
| 72 |
+
"eval_runtime": 80.224,
|
| 73 |
+
"eval_samples_per_second": 173.439,
|
| 74 |
+
"eval_steps_per_second": 7.23,
|
| 75 |
+
"step": 3000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.333555703802535,
|
| 79 |
+
"grad_norm": 1.7604336738586426,
|
| 80 |
+
"learning_rate": 0.000177762953079831,
|
| 81 |
+
"loss": 2.1074,
|
| 82 |
+
"step": 3500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.3812065186314686,
|
| 86 |
+
"grad_norm": 1.34886634349823,
|
| 87 |
+
"learning_rate": 0.00017458623209123543,
|
| 88 |
+
"loss": 2.0926,
|
| 89 |
+
"step": 4000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.3812065186314686,
|
| 93 |
+
"eval_loss": 2.3420486450195312,
|
| 94 |
+
"eval_runtime": 80.1942,
|
| 95 |
+
"eval_samples_per_second": 173.504,
|
| 96 |
+
"eval_steps_per_second": 7.232,
|
| 97 |
+
"step": 4000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.42885733346040217,
|
| 101 |
+
"grad_norm": 1.3510360717773438,
|
| 102 |
+
"learning_rate": 0.00017140951110263986,
|
| 103 |
+
"loss": 2.074,
|
| 104 |
+
"step": 4500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.47650814828933574,
|
| 108 |
+
"grad_norm": 1.272275447845459,
|
| 109 |
+
"learning_rate": 0.0001682327901140443,
|
| 110 |
+
"loss": 2.0752,
|
| 111 |
+
"step": 5000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.47650814828933574,
|
| 115 |
+
"eval_loss": 2.3270885944366455,
|
| 116 |
+
"eval_runtime": 80.2619,
|
| 117 |
+
"eval_samples_per_second": 173.358,
|
| 118 |
+
"eval_steps_per_second": 7.226,
|
| 119 |
+
"step": 5000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.5241589631182694,
|
| 123 |
+
"grad_norm": 1.289753794670105,
|
| 124 |
+
"learning_rate": 0.0001650560691254487,
|
| 125 |
+
"loss": 2.0487,
|
| 126 |
+
"step": 5500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.5718097779472029,
|
| 130 |
+
"grad_norm": 1.1615971326828003,
|
| 131 |
+
"learning_rate": 0.00016187934813685314,
|
| 132 |
+
"loss": 2.0437,
|
| 133 |
+
"step": 6000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.5718097779472029,
|
| 137 |
+
"eval_loss": 2.3274528980255127,
|
| 138 |
+
"eval_runtime": 80.2214,
|
| 139 |
+
"eval_samples_per_second": 173.445,
|
| 140 |
+
"eval_steps_per_second": 7.23,
|
| 141 |
+
"step": 6000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.6194605927761365,
|
| 145 |
+
"grad_norm": 1.3484673500061035,
|
| 146 |
+
"learning_rate": 0.00015870262714825757,
|
| 147 |
+
"loss": 2.0134,
|
| 148 |
+
"step": 6500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.66711140760507,
|
| 152 |
+
"grad_norm": 1.4737777709960938,
|
| 153 |
+
"learning_rate": 0.000155525906159662,
|
| 154 |
+
"loss": 2.0379,
|
| 155 |
+
"step": 7000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.66711140760507,
|
| 159 |
+
"eval_loss": 2.3164169788360596,
|
| 160 |
+
"eval_runtime": 80.2177,
|
| 161 |
+
"eval_samples_per_second": 173.453,
|
| 162 |
+
"eval_steps_per_second": 7.23,
|
| 163 |
+
"step": 7000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7147622224340037,
|
| 167 |
+
"grad_norm": 1.1502068042755127,
|
| 168 |
+
"learning_rate": 0.00015234918517106642,
|
| 169 |
+
"loss": 1.9916,
|
| 170 |
+
"step": 7500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7624130372629372,
|
| 174 |
+
"grad_norm": 1.2299320697784424,
|
| 175 |
+
"learning_rate": 0.00014917246418247085,
|
| 176 |
+
"loss": 2.0068,
|
| 177 |
+
"step": 8000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7624130372629372,
|
| 181 |
+
"eval_loss": 2.311408042907715,
|
| 182 |
+
"eval_runtime": 80.2576,
|
| 183 |
+
"eval_samples_per_second": 173.367,
|
| 184 |
+
"eval_steps_per_second": 7.227,
|
| 185 |
+
"step": 8000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.8100638520918708,
|
| 189 |
+
"grad_norm": 1.2537345886230469,
|
| 190 |
+
"learning_rate": 0.00014599574319387528,
|
| 191 |
+
"loss": 1.9886,
|
| 192 |
+
"step": 8500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.8577146669208043,
|
| 196 |
+
"grad_norm": 1.0486429929733276,
|
| 197 |
+
"learning_rate": 0.00014281902220527972,
|
| 198 |
+
"loss": 1.9882,
|
| 199 |
+
"step": 9000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.8577146669208043,
|
| 203 |
+
"eval_loss": 2.304290294647217,
|
| 204 |
+
"eval_runtime": 80.1372,
|
| 205 |
+
"eval_samples_per_second": 173.627,
|
| 206 |
+
"eval_steps_per_second": 7.238,
|
| 207 |
+
"step": 9000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.905365481749738,
|
| 211 |
+
"grad_norm": 1.1815516948699951,
|
| 212 |
+
"learning_rate": 0.00013964230121668413,
|
| 213 |
+
"loss": 1.9732,
|
| 214 |
+
"step": 9500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.9530162965786715,
|
| 218 |
+
"grad_norm": 1.2301689386367798,
|
| 219 |
+
"learning_rate": 0.0001364655802280886,
|
| 220 |
+
"loss": 1.9787,
|
| 221 |
+
"step": 10000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.9530162965786715,
|
| 225 |
+
"eval_loss": 2.2939772605895996,
|
| 226 |
+
"eval_runtime": 80.1592,
|
| 227 |
+
"eval_samples_per_second": 173.579,
|
| 228 |
+
"eval_steps_per_second": 7.236,
|
| 229 |
+
"step": 10000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.0006671114076051,
|
| 233 |
+
"grad_norm": 1.497831106185913,
|
| 234 |
+
"learning_rate": 0.000133288859239493,
|
| 235 |
+
"loss": 1.9557,
|
| 236 |
+
"step": 10500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.0483179262365387,
|
| 240 |
+
"grad_norm": 1.3323341608047485,
|
| 241 |
+
"learning_rate": 0.00013011213825089743,
|
| 242 |
+
"loss": 1.7231,
|
| 243 |
+
"step": 11000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.0483179262365387,
|
| 247 |
+
"eval_loss": 2.313231945037842,
|
| 248 |
+
"eval_runtime": 80.1199,
|
| 249 |
+
"eval_samples_per_second": 173.665,
|
| 250 |
+
"eval_steps_per_second": 7.239,
|
| 251 |
+
"step": 11000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.0959687410654722,
|
| 255 |
+
"grad_norm": 1.8000659942626953,
|
| 256 |
+
"learning_rate": 0.00012693541726230184,
|
| 257 |
+
"loss": 1.714,
|
| 258 |
+
"step": 11500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.1436195558944058,
|
| 262 |
+
"grad_norm": 1.2369180917739868,
|
| 263 |
+
"learning_rate": 0.0001237586962737063,
|
| 264 |
+
"loss": 1.7114,
|
| 265 |
+
"step": 12000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.1436195558944058,
|
| 269 |
+
"eval_loss": 2.313917875289917,
|
| 270 |
+
"eval_runtime": 80.1492,
|
| 271 |
+
"eval_samples_per_second": 173.601,
|
| 272 |
+
"eval_steps_per_second": 7.237,
|
| 273 |
+
"step": 12000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.1912703707233394,
|
| 277 |
+
"grad_norm": 1.431038498878479,
|
| 278 |
+
"learning_rate": 0.0001205819752851107,
|
| 279 |
+
"loss": 1.7283,
|
| 280 |
+
"step": 12500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.238921185552273,
|
| 284 |
+
"grad_norm": 1.4570106267929077,
|
| 285 |
+
"learning_rate": 0.00011740525429651514,
|
| 286 |
+
"loss": 1.7033,
|
| 287 |
+
"step": 13000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.238921185552273,
|
| 291 |
+
"eval_loss": 2.310853958129883,
|
| 292 |
+
"eval_runtime": 80.0945,
|
| 293 |
+
"eval_samples_per_second": 173.72,
|
| 294 |
+
"eval_steps_per_second": 7.241,
|
| 295 |
+
"step": 13000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.2865720003812064,
|
| 299 |
+
"grad_norm": 1.557187795639038,
|
| 300 |
+
"learning_rate": 0.00011422853330791956,
|
| 301 |
+
"loss": 1.7289,
|
| 302 |
+
"step": 13500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.33422281521014,
|
| 306 |
+
"grad_norm": 1.5775034427642822,
|
| 307 |
+
"learning_rate": 0.000111051812319324,
|
| 308 |
+
"loss": 1.7151,
|
| 309 |
+
"step": 14000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.33422281521014,
|
| 313 |
+
"eval_loss": 2.300920009613037,
|
| 314 |
+
"eval_runtime": 80.1537,
|
| 315 |
+
"eval_samples_per_second": 173.591,
|
| 316 |
+
"eval_steps_per_second": 7.236,
|
| 317 |
+
"step": 14000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.3818736300390737,
|
| 321 |
+
"grad_norm": 1.2451566457748413,
|
| 322 |
+
"learning_rate": 0.00010787509133072841,
|
| 323 |
+
"loss": 1.7218,
|
| 324 |
+
"step": 14500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.4295244448680071,
|
| 328 |
+
"grad_norm": 1.650688886642456,
|
| 329 |
+
"learning_rate": 0.00010469837034213286,
|
| 330 |
+
"loss": 1.7202,
|
| 331 |
+
"step": 15000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.4295244448680071,
|
| 335 |
+
"eval_loss": 2.290478467941284,
|
| 336 |
+
"eval_runtime": 80.1852,
|
| 337 |
+
"eval_samples_per_second": 173.523,
|
| 338 |
+
"eval_steps_per_second": 7.233,
|
| 339 |
+
"step": 15000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4771752596969407,
|
| 343 |
+
"grad_norm": 1.4705020189285278,
|
| 344 |
+
"learning_rate": 0.00010152164935353727,
|
| 345 |
+
"loss": 1.721,
|
| 346 |
+
"step": 15500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.5248260745258744,
|
| 350 |
+
"grad_norm": 1.530394434928894,
|
| 351 |
+
"learning_rate": 9.834492836494172e-05,
|
| 352 |
+
"loss": 1.7261,
|
| 353 |
+
"step": 16000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5248260745258744,
|
| 357 |
+
"eval_loss": 2.2944624423980713,
|
| 358 |
+
"eval_runtime": 80.1122,
|
| 359 |
+
"eval_samples_per_second": 173.682,
|
| 360 |
+
"eval_steps_per_second": 7.24,
|
| 361 |
+
"step": 16000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.572476889354808,
|
| 365 |
+
"grad_norm": 1.667024850845337,
|
| 366 |
+
"learning_rate": 9.516820737634614e-05,
|
| 367 |
+
"loss": 1.7072,
|
| 368 |
+
"step": 16500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.6201277041837416,
|
| 372 |
+
"grad_norm": 1.4624521732330322,
|
| 373 |
+
"learning_rate": 9.199148638775057e-05,
|
| 374 |
+
"loss": 1.7091,
|
| 375 |
+
"step": 17000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.6201277041837416,
|
| 379 |
+
"eval_loss": 2.2861549854278564,
|
| 380 |
+
"eval_runtime": 80.0947,
|
| 381 |
+
"eval_samples_per_second": 173.719,
|
| 382 |
+
"eval_steps_per_second": 7.241,
|
| 383 |
+
"step": 17000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.6677785190126753,
|
| 387 |
+
"grad_norm": 1.7141919136047363,
|
| 388 |
+
"learning_rate": 8.881476539915499e-05,
|
| 389 |
+
"loss": 1.7281,
|
| 390 |
+
"step": 17500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.7154293338416087,
|
| 394 |
+
"grad_norm": 1.367767333984375,
|
| 395 |
+
"learning_rate": 8.563804441055943e-05,
|
| 396 |
+
"loss": 1.7098,
|
| 397 |
+
"step": 18000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.7154293338416087,
|
| 401 |
+
"eval_loss": 2.2811758518218994,
|
| 402 |
+
"eval_runtime": 80.1424,
|
| 403 |
+
"eval_samples_per_second": 173.616,
|
| 404 |
+
"eval_steps_per_second": 7.237,
|
| 405 |
+
"step": 18000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.7630801486705423,
|
| 409 |
+
"grad_norm": 1.530991792678833,
|
| 410 |
+
"learning_rate": 8.246132342196385e-05,
|
| 411 |
+
"loss": 1.6994,
|
| 412 |
+
"step": 18500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.8107309634994757,
|
| 416 |
+
"grad_norm": 1.4421322345733643,
|
| 417 |
+
"learning_rate": 7.928460243336828e-05,
|
| 418 |
+
"loss": 1.6943,
|
| 419 |
+
"step": 19000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.8107309634994757,
|
| 423 |
+
"eval_loss": 2.273425579071045,
|
| 424 |
+
"eval_runtime": 80.1385,
|
| 425 |
+
"eval_samples_per_second": 173.624,
|
| 426 |
+
"eval_steps_per_second": 7.237,
|
| 427 |
+
"step": 19000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.8583817783284093,
|
| 431 |
+
"grad_norm": 1.5695687532424927,
|
| 432 |
+
"learning_rate": 7.610788144477272e-05,
|
| 433 |
+
"loss": 1.7,
|
| 434 |
+
"step": 19500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.906032593157343,
|
| 438 |
+
"grad_norm": 1.6507039070129395,
|
| 439 |
+
"learning_rate": 7.293116045617714e-05,
|
| 440 |
+
"loss": 1.7035,
|
| 441 |
+
"step": 20000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.906032593157343,
|
| 445 |
+
"eval_loss": 2.266268730163574,
|
| 446 |
+
"eval_runtime": 80.1631,
|
| 447 |
+
"eval_samples_per_second": 173.571,
|
| 448 |
+
"eval_steps_per_second": 7.235,
|
| 449 |
+
"step": 20000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.9536834079862766,
|
| 453 |
+
"grad_norm": 1.41545832157135,
|
| 454 |
+
"learning_rate": 6.975443946758157e-05,
|
| 455 |
+
"loss": 1.6948,
|
| 456 |
+
"step": 20500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.0013342228152102,
|
| 460 |
+
"grad_norm": 1.3855451345443726,
|
| 461 |
+
"learning_rate": 6.657771847898599e-05,
|
| 462 |
+
"loss": 1.6776,
|
| 463 |
+
"step": 21000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.0013342228152102,
|
| 467 |
+
"eval_loss": 2.302978515625,
|
| 468 |
+
"eval_runtime": 80.1675,
|
| 469 |
+
"eval_samples_per_second": 173.562,
|
| 470 |
+
"eval_steps_per_second": 7.235,
|
| 471 |
+
"step": 21000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.048985037644144,
|
| 475 |
+
"grad_norm": 1.3997050523757935,
|
| 476 |
+
"learning_rate": 6.340099749039043e-05,
|
| 477 |
+
"loss": 1.438,
|
| 478 |
+
"step": 21500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.0966358524730775,
|
| 482 |
+
"grad_norm": 1.4828859567642212,
|
| 483 |
+
"learning_rate": 6.0224276501794854e-05,
|
| 484 |
+
"loss": 1.4406,
|
| 485 |
+
"step": 22000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.0966358524730775,
|
| 489 |
+
"eval_loss": 2.3172175884246826,
|
| 490 |
+
"eval_runtime": 80.1748,
|
| 491 |
+
"eval_samples_per_second": 173.546,
|
| 492 |
+
"eval_steps_per_second": 7.234,
|
| 493 |
+
"step": 22000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.1442866673020107,
|
| 497 |
+
"grad_norm": 1.8176885843276978,
|
| 498 |
+
"learning_rate": 5.704755551319928e-05,
|
| 499 |
+
"loss": 1.4555,
|
| 500 |
+
"step": 22500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.1919374821309443,
|
| 504 |
+
"grad_norm": 1.48106050491333,
|
| 505 |
+
"learning_rate": 5.387083452460371e-05,
|
| 506 |
+
"loss": 1.4659,
|
| 507 |
+
"step": 23000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.1919374821309443,
|
| 511 |
+
"eval_loss": 2.3182783126831055,
|
| 512 |
+
"eval_runtime": 80.2101,
|
| 513 |
+
"eval_samples_per_second": 173.47,
|
| 514 |
+
"eval_steps_per_second": 7.231,
|
| 515 |
+
"step": 23000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.239588296959878,
|
| 519 |
+
"grad_norm": 1.6957001686096191,
|
| 520 |
+
"learning_rate": 5.0694113536008136e-05,
|
| 521 |
+
"loss": 1.448,
|
| 522 |
+
"step": 23500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.2872391117888116,
|
| 526 |
+
"grad_norm": 1.3845641613006592,
|
| 527 |
+
"learning_rate": 4.7517392547412564e-05,
|
| 528 |
+
"loss": 1.4608,
|
| 529 |
+
"step": 24000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.2872391117888116,
|
| 533 |
+
"eval_loss": 2.318488836288452,
|
| 534 |
+
"eval_runtime": 80.1689,
|
| 535 |
+
"eval_samples_per_second": 173.559,
|
| 536 |
+
"eval_steps_per_second": 7.235,
|
| 537 |
+
"step": 24000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.334889926617745,
|
| 541 |
+
"grad_norm": 1.9913188219070435,
|
| 542 |
+
"learning_rate": 4.434067155881699e-05,
|
| 543 |
+
"loss": 1.439,
|
| 544 |
+
"step": 24500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.382540741446679,
|
| 548 |
+
"grad_norm": 1.8244202136993408,
|
| 549 |
+
"learning_rate": 4.116395057022142e-05,
|
| 550 |
+
"loss": 1.4423,
|
| 551 |
+
"step": 25000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.382540741446679,
|
| 555 |
+
"eval_loss": 2.3121349811553955,
|
| 556 |
+
"eval_runtime": 80.1537,
|
| 557 |
+
"eval_samples_per_second": 173.591,
|
| 558 |
+
"eval_steps_per_second": 7.236,
|
| 559 |
+
"step": 25000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.4301915562756125,
|
| 563 |
+
"grad_norm": 1.347023606300354,
|
| 564 |
+
"learning_rate": 3.7987229581625846e-05,
|
| 565 |
+
"loss": 1.4506,
|
| 566 |
+
"step": 25500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.477842371104546,
|
| 570 |
+
"grad_norm": 1.49163019657135,
|
| 571 |
+
"learning_rate": 3.481050859303028e-05,
|
| 572 |
+
"loss": 1.4378,
|
| 573 |
+
"step": 26000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.477842371104546,
|
| 577 |
+
"eval_loss": 2.3090391159057617,
|
| 578 |
+
"eval_runtime": 80.1708,
|
| 579 |
+
"eval_samples_per_second": 173.554,
|
| 580 |
+
"eval_steps_per_second": 7.235,
|
| 581 |
+
"step": 26000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.5254931859334793,
|
| 585 |
+
"grad_norm": 1.7945301532745361,
|
| 586 |
+
"learning_rate": 3.163378760443471e-05,
|
| 587 |
+
"loss": 1.4436,
|
| 588 |
+
"step": 26500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.573144000762413,
|
| 592 |
+
"grad_norm": 1.5082517862319946,
|
| 593 |
+
"learning_rate": 2.8457066615839136e-05,
|
| 594 |
+
"loss": 1.4277,
|
| 595 |
+
"step": 27000
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.573144000762413,
|
| 599 |
+
"eval_loss": 2.3082542419433594,
|
| 600 |
+
"eval_runtime": 80.1802,
|
| 601 |
+
"eval_samples_per_second": 173.534,
|
| 602 |
+
"eval_steps_per_second": 7.234,
|
| 603 |
+
"step": 27000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.6207948155913465,
|
| 607 |
+
"grad_norm": 1.4329321384429932,
|
| 608 |
+
"learning_rate": 2.5280345627243563e-05,
|
| 609 |
+
"loss": 1.4301,
|
| 610 |
+
"step": 27500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.66844563042028,
|
| 614 |
+
"grad_norm": 1.2606436014175415,
|
| 615 |
+
"learning_rate": 2.2103624638647987e-05,
|
| 616 |
+
"loss": 1.4251,
|
| 617 |
+
"step": 28000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.66844563042028,
|
| 621 |
+
"eval_loss": 2.2960703372955322,
|
| 622 |
+
"eval_runtime": 80.1531,
|
| 623 |
+
"eval_samples_per_second": 173.593,
|
| 624 |
+
"eval_steps_per_second": 7.236,
|
| 625 |
+
"step": 28000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.716096445249214,
|
| 629 |
+
"grad_norm": 1.4542068243026733,
|
| 630 |
+
"learning_rate": 1.8926903650052415e-05,
|
| 631 |
+
"loss": 1.4248,
|
| 632 |
+
"step": 28500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.7637472600781474,
|
| 636 |
+
"grad_norm": 1.6642916202545166,
|
| 637 |
+
"learning_rate": 1.5750182661456846e-05,
|
| 638 |
+
"loss": 1.4219,
|
| 639 |
+
"step": 29000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.7637472600781474,
|
| 643 |
+
"eval_loss": 2.296442985534668,
|
| 644 |
+
"eval_runtime": 80.1753,
|
| 645 |
+
"eval_samples_per_second": 173.545,
|
| 646 |
+
"eval_steps_per_second": 7.234,
|
| 647 |
+
"step": 29000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.811398074907081,
|
| 651 |
+
"grad_norm": 2.0301756858825684,
|
| 652 |
+
"learning_rate": 1.2573461672861273e-05,
|
| 653 |
+
"loss": 1.4281,
|
| 654 |
+
"step": 29500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.8590488897360142,
|
| 658 |
+
"grad_norm": 1.6031594276428223,
|
| 659 |
+
"learning_rate": 9.3967406842657e-06,
|
| 660 |
+
"loss": 1.434,
|
| 661 |
+
"step": 30000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.8590488897360142,
|
| 665 |
+
"eval_loss": 2.2933690547943115,
|
| 666 |
+
"eval_runtime": 80.1482,
|
| 667 |
+
"eval_samples_per_second": 173.603,
|
| 668 |
+
"eval_steps_per_second": 7.237,
|
| 669 |
+
"step": 30000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.9066997045649483,
|
| 673 |
+
"grad_norm": 1.6658378839492798,
|
| 674 |
+
"learning_rate": 6.22001969567013e-06,
|
| 675 |
+
"loss": 1.4291,
|
| 676 |
+
"step": 30500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.9543505193938815,
|
| 680 |
+
"grad_norm": 1.589982032775879,
|
| 681 |
+
"learning_rate": 3.0432987070745578e-06,
|
| 682 |
+
"loss": 1.4279,
|
| 683 |
+
"step": 31000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.9543505193938815,
|
| 687 |
+
"eval_loss": 2.2906086444854736,
|
| 688 |
+
"eval_runtime": 80.2746,
|
| 689 |
+
"eval_samples_per_second": 173.33,
|
| 690 |
+
"eval_steps_per_second": 7.225,
|
| 691 |
+
"step": 31000
|
| 692 |
+
}
|
| 693 |
+
],
|
| 694 |
+
"logging_steps": 500,
|
| 695 |
+
"max_steps": 31479,
|
| 696 |
+
"num_input_tokens_seen": 0,
|
| 697 |
+
"num_train_epochs": 3,
|
| 698 |
+
"save_steps": 50000,
|
| 699 |
+
"stateful_callbacks": {
|
| 700 |
+
"TrainerControl": {
|
| 701 |
+
"args": {
|
| 702 |
+
"should_epoch_stop": false,
|
| 703 |
+
"should_evaluate": false,
|
| 704 |
+
"should_log": false,
|
| 705 |
+
"should_save": true,
|
| 706 |
+
"should_training_stop": true
|
| 707 |
+
},
|
| 708 |
+
"attributes": {}
|
| 709 |
+
}
|
| 710 |
+
},
|
| 711 |
+
"total_flos": 4.934891962368e+16,
|
| 712 |
+
"train_batch_size": 24,
|
| 713 |
+
"trial_name": null,
|
| 714 |
+
"trial_params": null
|
| 715 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1cb82ad67a09d3ad34c485ce75404c4ecac9c33795cc43afad0edd89cf6d615
|
| 3 |
size 5176
|