upload new models
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +30 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/config.json +45 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/model.safetensors +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/optimizer.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/rng_state_0.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/rng_state_1.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/rng_state_2.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/rng_state_3.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/scheduler.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/trainer_state.json +0 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/training_args.bin +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/config.json +45 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/model.safetensors +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/optimizer.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/rng_state_0.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/rng_state_1.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/rng_state_2.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/rng_state_3.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/scheduler.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/trainer_state.json +2109 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/training_args.bin +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/config.json +45 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/model.safetensors +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/optimizer.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/rng_state_0.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/rng_state_1.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/rng_state_2.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/rng_state_3.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/scheduler.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/trainer_state.json +0 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/training_args.bin +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/config.json +45 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/model.safetensors +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/optimizer.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/rng_state_0.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/rng_state_1.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/rng_state_2.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/rng_state_3.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/scheduler.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/trainer_state.json +0 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/training_args.bin +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/config.json +45 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/model.safetensors +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/optimizer.pt +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/rng_state_0.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/rng_state_1.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/rng_state_2.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/rng_state_3.pth +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/runs/Nov24_20-04-23_nid005058/events.out.tfevents.1764007677.nid005058.100797.0 +3 -0
- modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/runs/Nov24_21-15-32_nid005065/events.out.tfevents.1764011958.nid005065.96324.0 +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,33 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/checkpoint-7500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/checkpoint-7500/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/checkpoint-2500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/checkpoint-2500/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/checkpoint-10000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/checkpoint-10000/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/checkpoint-5000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/checkpoint-5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/checkpoint-7500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/checkpoint-7500/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/checkpoint-2500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/checkpoint-2500/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/checkpoint-10000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/checkpoint-10000/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/checkpoint-5000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/checkpoint-5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
modernbert-crux-researchy-pos_low.neg_zero.b64_n512.1e-4.512/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
modernbert-crux-researchy-pos_high.neg_zero.b64_n512.1e-4.512/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000.0,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initializer_cutoff_factor": 2.0,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 1152,
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"local_attention": 128,
|
| 28 |
+
"local_rope_theta": 10000.0,
|
| 29 |
+
"max_position_embeddings": 8192,
|
| 30 |
+
"mlp_bias": false,
|
| 31 |
+
"mlp_dropout": 0.0,
|
| 32 |
+
"model_type": "modernbert",
|
| 33 |
+
"norm_bias": false,
|
| 34 |
+
"norm_eps": 1e-05,
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_hidden_layers": 22,
|
| 37 |
+
"pad_token_id": 50283,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 50282,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"transformers_version": "4.57.1",
|
| 44 |
+
"vocab_size": 50368
|
| 45 |
+
}
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b3f482e56a92f0760e27f700de46d09e3a07b0a89d3ef90808d0d6b22512827
|
| 3 |
+
size 298041696
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdd7dd2e666a3126c4ed005d62b97fc63ca51fad19f7d480fb83d6eac7bfbbd0
|
| 3 |
+
size 596170443
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cc940a8d556e924e63165a153482b7202c426188f75c20c24e12d424fd66480
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ffdae51287c04c7c26dda1477c56be872f0a72d6ef4c91eed718fc9815f5cd0
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a259d84200d732d2a50300986ac2bfeae195d6cd6b8a5965f25beb1168967c93
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be124d0a4382f6650d248da735663a65eb35d7e6648a020fa3373d621111b9f4
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d02be6d8bda4ea9c67040ed89f878acdc986bd4df3fbc60440a9d3eacca02d63
|
| 3 |
+
size 1465
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-10000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2454495470a309f29bcb6e17995a0f5eba177149759169fad892e69436e76b71
|
| 3 |
+
size 6161
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000.0,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initializer_cutoff_factor": 2.0,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 1152,
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"local_attention": 128,
|
| 28 |
+
"local_rope_theta": 10000.0,
|
| 29 |
+
"max_position_embeddings": 8192,
|
| 30 |
+
"mlp_bias": false,
|
| 31 |
+
"mlp_dropout": 0.0,
|
| 32 |
+
"model_type": "modernbert",
|
| 33 |
+
"norm_bias": false,
|
| 34 |
+
"norm_eps": 1e-05,
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_hidden_layers": 22,
|
| 37 |
+
"pad_token_id": 50283,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 50282,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"transformers_version": "4.57.1",
|
| 44 |
+
"vocab_size": 50368
|
| 45 |
+
}
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88926b3be5727f9d0cc432ab2c00dfc3cab66da501336e8c8a7e08188cc0de25
|
| 3 |
+
size 298041696
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:780374ad1143b7bbe5b73f25a7260aa5063a103a1169b688b4285124dcb04dcc
|
| 3 |
+
size 596170443
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc5f93e31a0565f25cdab8cb64ac40f6b2487598bdeee72c8799d758f746e3e8
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:316c6cb0557f77c216cfe2e924b163f13368a82f990227cc5ed4e8a4722b4bbe
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e070935bf8d6873a426186e0eead069e83b7e9ae6f369169b1ddaff6a6b56807
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46f0239de5c990a1b529ec7282211423e89ed96a66ad587b7c704ffcb7ed7446
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a752d3f24f72817376cd37ffda577fd802575961fb476ede3db67c3cc89113bf
|
| 3 |
+
size 1465
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,2109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.9623233908948194,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007849293563579277,
|
| 14 |
+
"grad_norm": 14.5625,
|
| 15 |
+
"learning_rate": 9e-07,
|
| 16 |
+
"loss": 5.5652,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015698587127158554,
|
| 21 |
+
"grad_norm": 19.375,
|
| 22 |
+
"learning_rate": 1.9e-06,
|
| 23 |
+
"loss": 5.5182,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.023547880690737835,
|
| 28 |
+
"grad_norm": 24.125,
|
| 29 |
+
"learning_rate": 2.9e-06,
|
| 30 |
+
"loss": 5.5611,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03139717425431711,
|
| 35 |
+
"grad_norm": 28.875,
|
| 36 |
+
"learning_rate": 3.9e-06,
|
| 37 |
+
"loss": 5.5963,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03924646781789639,
|
| 42 |
+
"grad_norm": 12.6875,
|
| 43 |
+
"learning_rate": 4.9000000000000005e-06,
|
| 44 |
+
"loss": 5.5814,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04709576138147567,
|
| 49 |
+
"grad_norm": 22.625,
|
| 50 |
+
"learning_rate": 5.9e-06,
|
| 51 |
+
"loss": 5.5784,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.054945054945054944,
|
| 56 |
+
"grad_norm": 25.375,
|
| 57 |
+
"learning_rate": 6.900000000000001e-06,
|
| 58 |
+
"loss": 5.5543,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06279434850863422,
|
| 63 |
+
"grad_norm": 18.625,
|
| 64 |
+
"learning_rate": 7.9e-06,
|
| 65 |
+
"loss": 5.4877,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0706436420722135,
|
| 70 |
+
"grad_norm": 20.875,
|
| 71 |
+
"learning_rate": 8.9e-06,
|
| 72 |
+
"loss": 5.4914,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07849293563579278,
|
| 77 |
+
"grad_norm": 22.625,
|
| 78 |
+
"learning_rate": 9.900000000000002e-06,
|
| 79 |
+
"loss": 5.4106,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.07849293563579278,
|
| 84 |
+
"eval/acc": 6.976744174957275,
|
| 85 |
+
"step": 100
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.07849293563579278,
|
| 89 |
+
"eval_loss": 4.994912147521973,
|
| 90 |
+
"eval_runtime": 2.5896,
|
| 91 |
+
"eval_samples_per_second": 16.605,
|
| 92 |
+
"eval_steps_per_second": 0.386,
|
| 93 |
+
"step": 100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08634222919937205,
|
| 97 |
+
"grad_norm": 20.375,
|
| 98 |
+
"learning_rate": 1.09e-05,
|
| 99 |
+
"loss": 5.4131,
|
| 100 |
+
"step": 110
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09419152276295134,
|
| 104 |
+
"grad_norm": 21.5,
|
| 105 |
+
"learning_rate": 1.19e-05,
|
| 106 |
+
"loss": 5.2636,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.10204081632653061,
|
| 111 |
+
"grad_norm": 23.125,
|
| 112 |
+
"learning_rate": 1.29e-05,
|
| 113 |
+
"loss": 5.1837,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10989010989010989,
|
| 118 |
+
"grad_norm": 21.875,
|
| 119 |
+
"learning_rate": 1.3900000000000002e-05,
|
| 120 |
+
"loss": 5.0497,
|
| 121 |
+
"step": 140
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.11773940345368916,
|
| 125 |
+
"grad_norm": 22.75,
|
| 126 |
+
"learning_rate": 1.49e-05,
|
| 127 |
+
"loss": 4.8203,
|
| 128 |
+
"step": 150
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.12558869701726844,
|
| 132 |
+
"grad_norm": 22.875,
|
| 133 |
+
"learning_rate": 1.59e-05,
|
| 134 |
+
"loss": 4.6055,
|
| 135 |
+
"step": 160
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13343799058084774,
|
| 139 |
+
"grad_norm": 27.25,
|
| 140 |
+
"learning_rate": 1.69e-05,
|
| 141 |
+
"loss": 4.2194,
|
| 142 |
+
"step": 170
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.141287284144427,
|
| 146 |
+
"grad_norm": 26.375,
|
| 147 |
+
"learning_rate": 1.79e-05,
|
| 148 |
+
"loss": 3.8358,
|
| 149 |
+
"step": 180
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14913657770800628,
|
| 153 |
+
"grad_norm": 23.0,
|
| 154 |
+
"learning_rate": 1.8900000000000002e-05,
|
| 155 |
+
"loss": 3.4295,
|
| 156 |
+
"step": 190
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.15698587127158556,
|
| 160 |
+
"grad_norm": 70.5,
|
| 161 |
+
"learning_rate": 1.9900000000000003e-05,
|
| 162 |
+
"loss": 2.9421,
|
| 163 |
+
"step": 200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.15698587127158556,
|
| 167 |
+
"eval/acc": 9.302325248718262,
|
| 168 |
+
"step": 200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.15698587127158556,
|
| 172 |
+
"eval_loss": 3.6951303482055664,
|
| 173 |
+
"eval_runtime": 0.3137,
|
| 174 |
+
"eval_samples_per_second": 137.067,
|
| 175 |
+
"eval_steps_per_second": 3.188,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.16483516483516483,
|
| 180 |
+
"grad_norm": 21.625,
|
| 181 |
+
"learning_rate": 2.09e-05,
|
| 182 |
+
"loss": 2.8127,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.1726844583987441,
|
| 187 |
+
"grad_norm": 23.875,
|
| 188 |
+
"learning_rate": 2.19e-05,
|
| 189 |
+
"loss": 2.5715,
|
| 190 |
+
"step": 220
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.18053375196232338,
|
| 194 |
+
"grad_norm": 36.0,
|
| 195 |
+
"learning_rate": 2.29e-05,
|
| 196 |
+
"loss": 2.5288,
|
| 197 |
+
"step": 230
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.18838304552590268,
|
| 201 |
+
"grad_norm": 21.375,
|
| 202 |
+
"learning_rate": 2.39e-05,
|
| 203 |
+
"loss": 2.3737,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.19623233908948196,
|
| 208 |
+
"grad_norm": 22.75,
|
| 209 |
+
"learning_rate": 2.4900000000000002e-05,
|
| 210 |
+
"loss": 2.175,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.20408163265306123,
|
| 215 |
+
"grad_norm": 18.875,
|
| 216 |
+
"learning_rate": 2.5900000000000003e-05,
|
| 217 |
+
"loss": 2.2027,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.2119309262166405,
|
| 222 |
+
"grad_norm": 20.375,
|
| 223 |
+
"learning_rate": 2.6900000000000003e-05,
|
| 224 |
+
"loss": 2.0856,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.21978021978021978,
|
| 229 |
+
"grad_norm": 23.75,
|
| 230 |
+
"learning_rate": 2.7900000000000004e-05,
|
| 231 |
+
"loss": 2.0838,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.22762951334379905,
|
| 236 |
+
"grad_norm": 24.75,
|
| 237 |
+
"learning_rate": 2.8899999999999998e-05,
|
| 238 |
+
"loss": 1.967,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.23547880690737832,
|
| 243 |
+
"grad_norm": 26.375,
|
| 244 |
+
"learning_rate": 2.9900000000000002e-05,
|
| 245 |
+
"loss": 1.9612,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.23547880690737832,
|
| 250 |
+
"eval/acc": 20.930233001708984,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.23547880690737832,
|
| 255 |
+
"eval_loss": 3.1246371269226074,
|
| 256 |
+
"eval_runtime": 0.2117,
|
| 257 |
+
"eval_samples_per_second": 203.149,
|
| 258 |
+
"eval_steps_per_second": 4.724,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.24332810047095763,
|
| 263 |
+
"grad_norm": 57.75,
|
| 264 |
+
"learning_rate": 3.09e-05,
|
| 265 |
+
"loss": 1.8319,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.25117739403453687,
|
| 270 |
+
"grad_norm": 34.0,
|
| 271 |
+
"learning_rate": 3.19e-05,
|
| 272 |
+
"loss": 1.9554,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.25902668759811615,
|
| 277 |
+
"grad_norm": 36.0,
|
| 278 |
+
"learning_rate": 3.29e-05,
|
| 279 |
+
"loss": 1.8817,
|
| 280 |
+
"step": 330
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.2668759811616955,
|
| 284 |
+
"grad_norm": 21.5,
|
| 285 |
+
"learning_rate": 3.3900000000000004e-05,
|
| 286 |
+
"loss": 1.8154,
|
| 287 |
+
"step": 340
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.27472527472527475,
|
| 291 |
+
"grad_norm": 12.625,
|
| 292 |
+
"learning_rate": 3.49e-05,
|
| 293 |
+
"loss": 1.6854,
|
| 294 |
+
"step": 350
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.282574568288854,
|
| 298 |
+
"grad_norm": 23.125,
|
| 299 |
+
"learning_rate": 3.59e-05,
|
| 300 |
+
"loss": 1.6752,
|
| 301 |
+
"step": 360
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.2904238618524333,
|
| 305 |
+
"grad_norm": 16.375,
|
| 306 |
+
"learning_rate": 3.69e-05,
|
| 307 |
+
"loss": 1.6606,
|
| 308 |
+
"step": 370
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.29827315541601257,
|
| 312 |
+
"grad_norm": 22.5,
|
| 313 |
+
"learning_rate": 3.79e-05,
|
| 314 |
+
"loss": 1.6078,
|
| 315 |
+
"step": 380
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.30612244897959184,
|
| 319 |
+
"grad_norm": 16.625,
|
| 320 |
+
"learning_rate": 3.8900000000000004e-05,
|
| 321 |
+
"loss": 1.6903,
|
| 322 |
+
"step": 390
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.3139717425431711,
|
| 326 |
+
"grad_norm": 16.0,
|
| 327 |
+
"learning_rate": 3.99e-05,
|
| 328 |
+
"loss": 1.5474,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.3139717425431711,
|
| 333 |
+
"eval/acc": 30.23255729675293,
|
| 334 |
+
"step": 400
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.3139717425431711,
|
| 338 |
+
"eval_loss": 2.844658136367798,
|
| 339 |
+
"eval_runtime": 0.2112,
|
| 340 |
+
"eval_samples_per_second": 203.56,
|
| 341 |
+
"eval_steps_per_second": 4.734,
|
| 342 |
+
"step": 400
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.3218210361067504,
|
| 346 |
+
"grad_norm": 20.0,
|
| 347 |
+
"learning_rate": 4.09e-05,
|
| 348 |
+
"loss": 1.5915,
|
| 349 |
+
"step": 410
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.32967032967032966,
|
| 353 |
+
"grad_norm": 21.25,
|
| 354 |
+
"learning_rate": 4.19e-05,
|
| 355 |
+
"loss": 1.6112,
|
| 356 |
+
"step": 420
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.33751962323390894,
|
| 360 |
+
"grad_norm": 14.6875,
|
| 361 |
+
"learning_rate": 4.29e-05,
|
| 362 |
+
"loss": 1.5068,
|
| 363 |
+
"step": 430
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.3453689167974882,
|
| 367 |
+
"grad_norm": 19.25,
|
| 368 |
+
"learning_rate": 4.39e-05,
|
| 369 |
+
"loss": 1.4728,
|
| 370 |
+
"step": 440
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.3532182103610675,
|
| 374 |
+
"grad_norm": 16.75,
|
| 375 |
+
"learning_rate": 4.49e-05,
|
| 376 |
+
"loss": 1.3553,
|
| 377 |
+
"step": 450
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.36106750392464676,
|
| 381 |
+
"grad_norm": 13.0625,
|
| 382 |
+
"learning_rate": 4.5900000000000004e-05,
|
| 383 |
+
"loss": 1.4696,
|
| 384 |
+
"step": 460
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.36891679748822603,
|
| 388 |
+
"grad_norm": 18.875,
|
| 389 |
+
"learning_rate": 4.69e-05,
|
| 390 |
+
"loss": 1.4953,
|
| 391 |
+
"step": 470
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.37676609105180536,
|
| 395 |
+
"grad_norm": 14.3125,
|
| 396 |
+
"learning_rate": 4.79e-05,
|
| 397 |
+
"loss": 1.3238,
|
| 398 |
+
"step": 480
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.38461538461538464,
|
| 402 |
+
"grad_norm": 83.0,
|
| 403 |
+
"learning_rate": 4.89e-05,
|
| 404 |
+
"loss": 1.5413,
|
| 405 |
+
"step": 490
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.3924646781789639,
|
| 409 |
+
"grad_norm": 13.1875,
|
| 410 |
+
"learning_rate": 4.99e-05,
|
| 411 |
+
"loss": 1.359,
|
| 412 |
+
"step": 500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.3924646781789639,
|
| 416 |
+
"eval/acc": 32.55813980102539,
|
| 417 |
+
"step": 500
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.3924646781789639,
|
| 421 |
+
"eval_loss": 2.6606061458587646,
|
| 422 |
+
"eval_runtime": 0.2618,
|
| 423 |
+
"eval_samples_per_second": 164.247,
|
| 424 |
+
"eval_steps_per_second": 3.82,
|
| 425 |
+
"step": 500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.4003139717425432,
|
| 429 |
+
"grad_norm": 27.125,
|
| 430 |
+
"learning_rate": 5.0900000000000004e-05,
|
| 431 |
+
"loss": 1.3117,
|
| 432 |
+
"step": 510
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.40816326530612246,
|
| 436 |
+
"grad_norm": 13.5,
|
| 437 |
+
"learning_rate": 5.19e-05,
|
| 438 |
+
"loss": 1.4346,
|
| 439 |
+
"step": 520
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.41601255886970173,
|
| 443 |
+
"grad_norm": 15.25,
|
| 444 |
+
"learning_rate": 5.2900000000000005e-05,
|
| 445 |
+
"loss": 1.3777,
|
| 446 |
+
"step": 530
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.423861852433281,
|
| 450 |
+
"grad_norm": 16.75,
|
| 451 |
+
"learning_rate": 5.390000000000001e-05,
|
| 452 |
+
"loss": 1.4117,
|
| 453 |
+
"step": 540
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.4317111459968603,
|
| 457 |
+
"grad_norm": 10.5625,
|
| 458 |
+
"learning_rate": 5.4900000000000006e-05,
|
| 459 |
+
"loss": 1.2607,
|
| 460 |
+
"step": 550
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.43956043956043955,
|
| 464 |
+
"grad_norm": 19.125,
|
| 465 |
+
"learning_rate": 5.590000000000001e-05,
|
| 466 |
+
"loss": 1.3393,
|
| 467 |
+
"step": 560
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.4474097331240188,
|
| 471 |
+
"grad_norm": 15.25,
|
| 472 |
+
"learning_rate": 5.69e-05,
|
| 473 |
+
"loss": 1.3033,
|
| 474 |
+
"step": 570
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.4552590266875981,
|
| 478 |
+
"grad_norm": 16.5,
|
| 479 |
+
"learning_rate": 5.79e-05,
|
| 480 |
+
"loss": 1.343,
|
| 481 |
+
"step": 580
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.4631083202511774,
|
| 485 |
+
"grad_norm": 10.75,
|
| 486 |
+
"learning_rate": 5.89e-05,
|
| 487 |
+
"loss": 1.368,
|
| 488 |
+
"step": 590
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.47095761381475665,
|
| 492 |
+
"grad_norm": 14.125,
|
| 493 |
+
"learning_rate": 5.99e-05,
|
| 494 |
+
"loss": 1.2961,
|
| 495 |
+
"step": 600
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.47095761381475665,
|
| 499 |
+
"eval/acc": 32.55813980102539,
|
| 500 |
+
"step": 600
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.47095761381475665,
|
| 504 |
+
"eval_loss": 2.6568233966827393,
|
| 505 |
+
"eval_runtime": 0.404,
|
| 506 |
+
"eval_samples_per_second": 106.439,
|
| 507 |
+
"eval_steps_per_second": 2.475,
|
| 508 |
+
"step": 600
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.478806907378336,
|
| 512 |
+
"grad_norm": 11.9375,
|
| 513 |
+
"learning_rate": 6.09e-05,
|
| 514 |
+
"loss": 1.2873,
|
| 515 |
+
"step": 610
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.48665620094191525,
|
| 519 |
+
"grad_norm": 11.0625,
|
| 520 |
+
"learning_rate": 6.19e-05,
|
| 521 |
+
"loss": 1.2009,
|
| 522 |
+
"step": 620
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.4945054945054945,
|
| 526 |
+
"grad_norm": 11.1875,
|
| 527 |
+
"learning_rate": 6.29e-05,
|
| 528 |
+
"loss": 1.2291,
|
| 529 |
+
"step": 630
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.5023547880690737,
|
| 533 |
+
"grad_norm": 13.75,
|
| 534 |
+
"learning_rate": 6.390000000000001e-05,
|
| 535 |
+
"loss": 1.2247,
|
| 536 |
+
"step": 640
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.5102040816326531,
|
| 540 |
+
"grad_norm": 25.25,
|
| 541 |
+
"learning_rate": 6.49e-05,
|
| 542 |
+
"loss": 1.3554,
|
| 543 |
+
"step": 650
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.5180533751962323,
|
| 547 |
+
"grad_norm": 12.6875,
|
| 548 |
+
"learning_rate": 6.59e-05,
|
| 549 |
+
"loss": 1.1111,
|
| 550 |
+
"step": 660
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.5259026687598116,
|
| 554 |
+
"grad_norm": 11.875,
|
| 555 |
+
"learning_rate": 6.690000000000001e-05,
|
| 556 |
+
"loss": 1.2274,
|
| 557 |
+
"step": 670
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.533751962323391,
|
| 561 |
+
"grad_norm": 13.0625,
|
| 562 |
+
"learning_rate": 6.790000000000001e-05,
|
| 563 |
+
"loss": 1.2189,
|
| 564 |
+
"step": 680
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.5416012558869702,
|
| 568 |
+
"grad_norm": 11.5625,
|
| 569 |
+
"learning_rate": 6.89e-05,
|
| 570 |
+
"loss": 1.2304,
|
| 571 |
+
"step": 690
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.5494505494505495,
|
| 575 |
+
"grad_norm": 13.3125,
|
| 576 |
+
"learning_rate": 6.99e-05,
|
| 577 |
+
"loss": 1.2443,
|
| 578 |
+
"step": 700
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.5494505494505495,
|
| 582 |
+
"eval/acc": 37.20930099487305,
|
| 583 |
+
"step": 700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5494505494505495,
|
| 587 |
+
"eval_loss": 2.6640543937683105,
|
| 588 |
+
"eval_runtime": 0.3416,
|
| 589 |
+
"eval_samples_per_second": 125.888,
|
| 590 |
+
"eval_steps_per_second": 2.928,
|
| 591 |
+
"step": 700
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.5572998430141287,
|
| 595 |
+
"grad_norm": 9.4375,
|
| 596 |
+
"learning_rate": 7.09e-05,
|
| 597 |
+
"loss": 1.1122,
|
| 598 |
+
"step": 710
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.565149136577708,
|
| 602 |
+
"grad_norm": 10.3125,
|
| 603 |
+
"learning_rate": 7.19e-05,
|
| 604 |
+
"loss": 1.0981,
|
| 605 |
+
"step": 720
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.5729984301412873,
|
| 609 |
+
"grad_norm": 15.5,
|
| 610 |
+
"learning_rate": 7.29e-05,
|
| 611 |
+
"loss": 1.2359,
|
| 612 |
+
"step": 730
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.5808477237048666,
|
| 616 |
+
"grad_norm": 21.375,
|
| 617 |
+
"learning_rate": 7.390000000000001e-05,
|
| 618 |
+
"loss": 1.0989,
|
| 619 |
+
"step": 740
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.5886970172684458,
|
| 623 |
+
"grad_norm": 13.25,
|
| 624 |
+
"learning_rate": 7.49e-05,
|
| 625 |
+
"loss": 1.2595,
|
| 626 |
+
"step": 750
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.5965463108320251,
|
| 630 |
+
"grad_norm": 10.375,
|
| 631 |
+
"learning_rate": 7.59e-05,
|
| 632 |
+
"loss": 1.2028,
|
| 633 |
+
"step": 760
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.6043956043956044,
|
| 637 |
+
"grad_norm": 12.1875,
|
| 638 |
+
"learning_rate": 7.69e-05,
|
| 639 |
+
"loss": 1.1712,
|
| 640 |
+
"step": 770
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6122448979591837,
|
| 644 |
+
"grad_norm": 10.3125,
|
| 645 |
+
"learning_rate": 7.790000000000001e-05,
|
| 646 |
+
"loss": 1.0643,
|
| 647 |
+
"step": 780
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.6200941915227629,
|
| 651 |
+
"grad_norm": 11.8125,
|
| 652 |
+
"learning_rate": 7.890000000000001e-05,
|
| 653 |
+
"loss": 1.2406,
|
| 654 |
+
"step": 790
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.6279434850863422,
|
| 658 |
+
"grad_norm": 12.0,
|
| 659 |
+
"learning_rate": 7.99e-05,
|
| 660 |
+
"loss": 1.13,
|
| 661 |
+
"step": 800
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.6279434850863422,
|
| 665 |
+
"eval/acc": 37.20930099487305,
|
| 666 |
+
"step": 800
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.6279434850863422,
|
| 670 |
+
"eval_loss": 2.728229284286499,
|
| 671 |
+
"eval_runtime": 0.3718,
|
| 672 |
+
"eval_samples_per_second": 115.661,
|
| 673 |
+
"eval_steps_per_second": 2.69,
|
| 674 |
+
"step": 800
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6357927786499215,
|
| 678 |
+
"grad_norm": 10.125,
|
| 679 |
+
"learning_rate": 8.090000000000001e-05,
|
| 680 |
+
"loss": 1.1834,
|
| 681 |
+
"step": 810
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6436420722135008,
|
| 685 |
+
"grad_norm": 11.0625,
|
| 686 |
+
"learning_rate": 8.19e-05,
|
| 687 |
+
"loss": 1.1268,
|
| 688 |
+
"step": 820
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6514913657770801,
|
| 692 |
+
"grad_norm": 12.375,
|
| 693 |
+
"learning_rate": 8.29e-05,
|
| 694 |
+
"loss": 1.0937,
|
| 695 |
+
"step": 830
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6593406593406593,
|
| 699 |
+
"grad_norm": 11.0,
|
| 700 |
+
"learning_rate": 8.39e-05,
|
| 701 |
+
"loss": 1.1011,
|
| 702 |
+
"step": 840
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.6671899529042387,
|
| 706 |
+
"grad_norm": 10.8125,
|
| 707 |
+
"learning_rate": 8.49e-05,
|
| 708 |
+
"loss": 1.1089,
|
| 709 |
+
"step": 850
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.6750392464678179,
|
| 713 |
+
"grad_norm": 10.25,
|
| 714 |
+
"learning_rate": 8.59e-05,
|
| 715 |
+
"loss": 1.1998,
|
| 716 |
+
"step": 860
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.6828885400313972,
|
| 720 |
+
"grad_norm": 11.4375,
|
| 721 |
+
"learning_rate": 8.69e-05,
|
| 722 |
+
"loss": 1.1822,
|
| 723 |
+
"step": 870
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6907378335949764,
|
| 727 |
+
"grad_norm": 9.6875,
|
| 728 |
+
"learning_rate": 8.790000000000001e-05,
|
| 729 |
+
"loss": 1.1285,
|
| 730 |
+
"step": 880
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.6985871271585558,
|
| 734 |
+
"grad_norm": 8.3125,
|
| 735 |
+
"learning_rate": 8.89e-05,
|
| 736 |
+
"loss": 1.1014,
|
| 737 |
+
"step": 890
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.706436420722135,
|
| 741 |
+
"grad_norm": 10.5625,
|
| 742 |
+
"learning_rate": 8.99e-05,
|
| 743 |
+
"loss": 1.0286,
|
| 744 |
+
"step": 900
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.706436420722135,
|
| 748 |
+
"eval/acc": 34.88372039794922,
|
| 749 |
+
"step": 900
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.706436420722135,
|
| 753 |
+
"eval_loss": 2.7974932193756104,
|
| 754 |
+
"eval_runtime": 0.2829,
|
| 755 |
+
"eval_samples_per_second": 151.994,
|
| 756 |
+
"eval_steps_per_second": 3.535,
|
| 757 |
+
"step": 900
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.7142857142857143,
|
| 761 |
+
"grad_norm": 9.4375,
|
| 762 |
+
"learning_rate": 9.090000000000001e-05,
|
| 763 |
+
"loss": 1.1923,
|
| 764 |
+
"step": 910
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.7221350078492935,
|
| 768 |
+
"grad_norm": 10.6875,
|
| 769 |
+
"learning_rate": 9.190000000000001e-05,
|
| 770 |
+
"loss": 1.1552,
|
| 771 |
+
"step": 920
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.7299843014128728,
|
| 775 |
+
"grad_norm": 13.0,
|
| 776 |
+
"learning_rate": 9.290000000000001e-05,
|
| 777 |
+
"loss": 1.0113,
|
| 778 |
+
"step": 930
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.7378335949764521,
|
| 782 |
+
"grad_norm": 7.96875,
|
| 783 |
+
"learning_rate": 9.39e-05,
|
| 784 |
+
"loss": 1.0184,
|
| 785 |
+
"step": 940
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.7456828885400314,
|
| 789 |
+
"grad_norm": 9.5,
|
| 790 |
+
"learning_rate": 9.49e-05,
|
| 791 |
+
"loss": 0.979,
|
| 792 |
+
"step": 950
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.7535321821036107,
|
| 796 |
+
"grad_norm": 9.875,
|
| 797 |
+
"learning_rate": 9.59e-05,
|
| 798 |
+
"loss": 1.0887,
|
| 799 |
+
"step": 960
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.7613814756671899,
|
| 803 |
+
"grad_norm": 7.71875,
|
| 804 |
+
"learning_rate": 9.69e-05,
|
| 805 |
+
"loss": 0.9731,
|
| 806 |
+
"step": 970
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.7692307692307693,
|
| 810 |
+
"grad_norm": 9.9375,
|
| 811 |
+
"learning_rate": 9.790000000000001e-05,
|
| 812 |
+
"loss": 1.0766,
|
| 813 |
+
"step": 980
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.7770800627943485,
|
| 817 |
+
"grad_norm": 8.6875,
|
| 818 |
+
"learning_rate": 9.89e-05,
|
| 819 |
+
"loss": 1.1194,
|
| 820 |
+
"step": 990
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.7849293563579278,
|
| 824 |
+
"grad_norm": 9.0625,
|
| 825 |
+
"learning_rate": 9.99e-05,
|
| 826 |
+
"loss": 1.0378,
|
| 827 |
+
"step": 1000
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.7849293563579278,
|
| 831 |
+
"eval/acc": 41.86046600341797,
|
| 832 |
+
"step": 1000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.7849293563579278,
|
| 836 |
+
"eval_loss": 2.767014741897583,
|
| 837 |
+
"eval_runtime": 0.3044,
|
| 838 |
+
"eval_samples_per_second": 141.238,
|
| 839 |
+
"eval_steps_per_second": 3.285,
|
| 840 |
+
"step": 1000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.792778649921507,
|
| 844 |
+
"grad_norm": 10.4375,
|
| 845 |
+
"learning_rate": 9.99e-05,
|
| 846 |
+
"loss": 0.9659,
|
| 847 |
+
"step": 1010
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.8006279434850864,
|
| 851 |
+
"grad_norm": 11.6875,
|
| 852 |
+
"learning_rate": 9.97888888888889e-05,
|
| 853 |
+
"loss": 1.1504,
|
| 854 |
+
"step": 1020
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.8084772370486656,
|
| 858 |
+
"grad_norm": 8.9375,
|
| 859 |
+
"learning_rate": 9.967777777777779e-05,
|
| 860 |
+
"loss": 1.0709,
|
| 861 |
+
"step": 1030
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.8163265306122449,
|
| 865 |
+
"grad_norm": 8.5625,
|
| 866 |
+
"learning_rate": 9.956666666666667e-05,
|
| 867 |
+
"loss": 1.0391,
|
| 868 |
+
"step": 1040
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.8241758241758241,
|
| 872 |
+
"grad_norm": 13.0625,
|
| 873 |
+
"learning_rate": 9.945555555555555e-05,
|
| 874 |
+
"loss": 1.0668,
|
| 875 |
+
"step": 1050
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.8320251177394035,
|
| 879 |
+
"grad_norm": 11.625,
|
| 880 |
+
"learning_rate": 9.934444444444445e-05,
|
| 881 |
+
"loss": 1.1143,
|
| 882 |
+
"step": 1060
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.8398744113029827,
|
| 886 |
+
"grad_norm": 9.125,
|
| 887 |
+
"learning_rate": 9.923333333333334e-05,
|
| 888 |
+
"loss": 1.1035,
|
| 889 |
+
"step": 1070
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.847723704866562,
|
| 893 |
+
"grad_norm": 10.25,
|
| 894 |
+
"learning_rate": 9.912222222222222e-05,
|
| 895 |
+
"loss": 1.0149,
|
| 896 |
+
"step": 1080
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.8555729984301413,
|
| 900 |
+
"grad_norm": 8.5,
|
| 901 |
+
"learning_rate": 9.901111111111112e-05,
|
| 902 |
+
"loss": 0.9739,
|
| 903 |
+
"step": 1090
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.8634222919937206,
|
| 907 |
+
"grad_norm": 9.6875,
|
| 908 |
+
"learning_rate": 9.89e-05,
|
| 909 |
+
"loss": 1.1187,
|
| 910 |
+
"step": 1100
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.8634222919937206,
|
| 914 |
+
"eval/acc": 41.86046600341797,
|
| 915 |
+
"step": 1100
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.8634222919937206,
|
| 919 |
+
"eval_loss": 2.7894911766052246,
|
| 920 |
+
"eval_runtime": 0.3266,
|
| 921 |
+
"eval_samples_per_second": 131.676,
|
| 922 |
+
"eval_steps_per_second": 3.062,
|
| 923 |
+
"step": 1100
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.8712715855572999,
|
| 927 |
+
"grad_norm": 7.96875,
|
| 928 |
+
"learning_rate": 9.87888888888889e-05,
|
| 929 |
+
"loss": 1.0221,
|
| 930 |
+
"step": 1110
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.8791208791208791,
|
| 934 |
+
"grad_norm": 11.8125,
|
| 935 |
+
"learning_rate": 9.867777777777777e-05,
|
| 936 |
+
"loss": 1.1126,
|
| 937 |
+
"step": 1120
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.8869701726844584,
|
| 941 |
+
"grad_norm": 10.625,
|
| 942 |
+
"learning_rate": 9.856666666666667e-05,
|
| 943 |
+
"loss": 0.916,
|
| 944 |
+
"step": 1130
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.8948194662480377,
|
| 948 |
+
"grad_norm": 8.6875,
|
| 949 |
+
"learning_rate": 9.845555555555556e-05,
|
| 950 |
+
"loss": 0.9863,
|
| 951 |
+
"step": 1140
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.902668759811617,
|
| 955 |
+
"grad_norm": 9.3125,
|
| 956 |
+
"learning_rate": 9.834444444444446e-05,
|
| 957 |
+
"loss": 0.937,
|
| 958 |
+
"step": 1150
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 0.9105180533751962,
|
| 962 |
+
"grad_norm": 12.75,
|
| 963 |
+
"learning_rate": 9.823333333333333e-05,
|
| 964 |
+
"loss": 0.9732,
|
| 965 |
+
"step": 1160
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.9183673469387755,
|
| 969 |
+
"grad_norm": 8.375,
|
| 970 |
+
"learning_rate": 9.812222222222223e-05,
|
| 971 |
+
"loss": 0.9896,
|
| 972 |
+
"step": 1170
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.9262166405023547,
|
| 976 |
+
"grad_norm": 9.125,
|
| 977 |
+
"learning_rate": 9.801111111111112e-05,
|
| 978 |
+
"loss": 1.0532,
|
| 979 |
+
"step": 1180
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 0.9340659340659341,
|
| 983 |
+
"grad_norm": 6.78125,
|
| 984 |
+
"learning_rate": 9.790000000000001e-05,
|
| 985 |
+
"loss": 1.0416,
|
| 986 |
+
"step": 1190
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.9419152276295133,
|
| 990 |
+
"grad_norm": 10.5,
|
| 991 |
+
"learning_rate": 9.778888888888889e-05,
|
| 992 |
+
"loss": 0.966,
|
| 993 |
+
"step": 1200
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.9419152276295133,
|
| 997 |
+
"eval/acc": 39.53488540649414,
|
| 998 |
+
"step": 1200
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.9419152276295133,
|
| 1002 |
+
"eval_loss": 2.8899922370910645,
|
| 1003 |
+
"eval_runtime": 0.2904,
|
| 1004 |
+
"eval_samples_per_second": 148.091,
|
| 1005 |
+
"eval_steps_per_second": 3.444,
|
| 1006 |
+
"step": 1200
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.9497645211930926,
|
| 1010 |
+
"grad_norm": 8.125,
|
| 1011 |
+
"learning_rate": 9.767777777777778e-05,
|
| 1012 |
+
"loss": 0.9864,
|
| 1013 |
+
"step": 1210
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.957613814756672,
|
| 1017 |
+
"grad_norm": 6.75,
|
| 1018 |
+
"learning_rate": 9.756666666666668e-05,
|
| 1019 |
+
"loss": 0.8145,
|
| 1020 |
+
"step": 1220
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.9654631083202512,
|
| 1024 |
+
"grad_norm": 9.125,
|
| 1025 |
+
"learning_rate": 9.745555555555556e-05,
|
| 1026 |
+
"loss": 0.9478,
|
| 1027 |
+
"step": 1230
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.9733124018838305,
|
| 1031 |
+
"grad_norm": 8.0,
|
| 1032 |
+
"learning_rate": 9.734444444444444e-05,
|
| 1033 |
+
"loss": 1.026,
|
| 1034 |
+
"step": 1240
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.9811616954474097,
|
| 1038 |
+
"grad_norm": 8.0,
|
| 1039 |
+
"learning_rate": 9.723333333333334e-05,
|
| 1040 |
+
"loss": 0.9368,
|
| 1041 |
+
"step": 1250
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.989010989010989,
|
| 1045 |
+
"grad_norm": 9.6875,
|
| 1046 |
+
"learning_rate": 9.712222222222223e-05,
|
| 1047 |
+
"loss": 0.9058,
|
| 1048 |
+
"step": 1260
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.9968602825745683,
|
| 1052 |
+
"grad_norm": 10.1875,
|
| 1053 |
+
"learning_rate": 9.701111111111111e-05,
|
| 1054 |
+
"loss": 0.7951,
|
| 1055 |
+
"step": 1270
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.0047095761381475,
|
| 1059 |
+
"grad_norm": 8.3125,
|
| 1060 |
+
"learning_rate": 9.69e-05,
|
| 1061 |
+
"loss": 0.9533,
|
| 1062 |
+
"step": 1280
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.012558869701727,
|
| 1066 |
+
"grad_norm": 10.5,
|
| 1067 |
+
"learning_rate": 9.67888888888889e-05,
|
| 1068 |
+
"loss": 0.9711,
|
| 1069 |
+
"step": 1290
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.0204081632653061,
|
| 1073 |
+
"grad_norm": 7.53125,
|
| 1074 |
+
"learning_rate": 9.667777777777778e-05,
|
| 1075 |
+
"loss": 0.9631,
|
| 1076 |
+
"step": 1300
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.0204081632653061,
|
| 1080 |
+
"eval/acc": 39.53488540649414,
|
| 1081 |
+
"step": 1300
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.0204081632653061,
|
| 1085 |
+
"eval_loss": 2.9734435081481934,
|
| 1086 |
+
"eval_runtime": 0.5345,
|
| 1087 |
+
"eval_samples_per_second": 80.449,
|
| 1088 |
+
"eval_steps_per_second": 1.871,
|
| 1089 |
+
"step": 1300
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.0282574568288854,
|
| 1093 |
+
"grad_norm": 8.75,
|
| 1094 |
+
"learning_rate": 9.656666666666668e-05,
|
| 1095 |
+
"loss": 0.8875,
|
| 1096 |
+
"step": 1310
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.0361067503924646,
|
| 1100 |
+
"grad_norm": 9.125,
|
| 1101 |
+
"learning_rate": 9.645555555555556e-05,
|
| 1102 |
+
"loss": 0.9751,
|
| 1103 |
+
"step": 1320
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.043956043956044,
|
| 1107 |
+
"grad_norm": 10.6875,
|
| 1108 |
+
"learning_rate": 9.634444444444445e-05,
|
| 1109 |
+
"loss": 0.8454,
|
| 1110 |
+
"step": 1330
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.0518053375196232,
|
| 1114 |
+
"grad_norm": 8.125,
|
| 1115 |
+
"learning_rate": 9.623333333333335e-05,
|
| 1116 |
+
"loss": 0.9487,
|
| 1117 |
+
"step": 1340
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.0596546310832025,
|
| 1121 |
+
"grad_norm": 9.1875,
|
| 1122 |
+
"learning_rate": 9.612222222222223e-05,
|
| 1123 |
+
"loss": 0.9746,
|
| 1124 |
+
"step": 1350
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.0675039246467817,
|
| 1128 |
+
"grad_norm": 11.1875,
|
| 1129 |
+
"learning_rate": 9.601111111111112e-05,
|
| 1130 |
+
"loss": 1.0248,
|
| 1131 |
+
"step": 1360
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.0753532182103611,
|
| 1135 |
+
"grad_norm": 8.0625,
|
| 1136 |
+
"learning_rate": 9.59e-05,
|
| 1137 |
+
"loss": 0.9127,
|
| 1138 |
+
"step": 1370
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.0832025117739403,
|
| 1142 |
+
"grad_norm": 9.6875,
|
| 1143 |
+
"learning_rate": 9.57888888888889e-05,
|
| 1144 |
+
"loss": 0.8629,
|
| 1145 |
+
"step": 1380
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.0910518053375196,
|
| 1149 |
+
"grad_norm": 8.25,
|
| 1150 |
+
"learning_rate": 9.567777777777778e-05,
|
| 1151 |
+
"loss": 1.0042,
|
| 1152 |
+
"step": 1390
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.098901098901099,
|
| 1156 |
+
"grad_norm": 15.0625,
|
| 1157 |
+
"learning_rate": 9.556666666666667e-05,
|
| 1158 |
+
"loss": 0.9498,
|
| 1159 |
+
"step": 1400
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 1.098901098901099,
|
| 1163 |
+
"eval/acc": 37.20930099487305,
|
| 1164 |
+
"step": 1400
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.098901098901099,
|
| 1168 |
+
"eval_loss": 2.8393633365631104,
|
| 1169 |
+
"eval_runtime": 0.219,
|
| 1170 |
+
"eval_samples_per_second": 196.342,
|
| 1171 |
+
"eval_steps_per_second": 4.566,
|
| 1172 |
+
"step": 1400
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.1067503924646782,
|
| 1176 |
+
"grad_norm": 10.0,
|
| 1177 |
+
"learning_rate": 9.545555555555557e-05,
|
| 1178 |
+
"loss": 0.9662,
|
| 1179 |
+
"step": 1410
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.1145996860282574,
|
| 1183 |
+
"grad_norm": 8.1875,
|
| 1184 |
+
"learning_rate": 9.534444444444445e-05,
|
| 1185 |
+
"loss": 0.9162,
|
| 1186 |
+
"step": 1420
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.1224489795918366,
|
| 1190 |
+
"grad_norm": 22.625,
|
| 1191 |
+
"learning_rate": 9.523333333333334e-05,
|
| 1192 |
+
"loss": 0.8393,
|
| 1193 |
+
"step": 1430
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.130298273155416,
|
| 1197 |
+
"grad_norm": 9.3125,
|
| 1198 |
+
"learning_rate": 9.512222222222222e-05,
|
| 1199 |
+
"loss": 1.0153,
|
| 1200 |
+
"step": 1440
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.1381475667189953,
|
| 1204 |
+
"grad_norm": 8.125,
|
| 1205 |
+
"learning_rate": 9.501111111111112e-05,
|
| 1206 |
+
"loss": 0.9047,
|
| 1207 |
+
"step": 1450
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.1459968602825745,
|
| 1211 |
+
"grad_norm": 9.3125,
|
| 1212 |
+
"learning_rate": 9.49e-05,
|
| 1213 |
+
"loss": 0.9004,
|
| 1214 |
+
"step": 1460
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.1538461538461537,
|
| 1218 |
+
"grad_norm": 7.40625,
|
| 1219 |
+
"learning_rate": 9.478888888888889e-05,
|
| 1220 |
+
"loss": 0.8594,
|
| 1221 |
+
"step": 1470
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.1616954474097332,
|
| 1225 |
+
"grad_norm": 9.625,
|
| 1226 |
+
"learning_rate": 9.467777777777779e-05,
|
| 1227 |
+
"loss": 0.8658,
|
| 1228 |
+
"step": 1480
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.1695447409733124,
|
| 1232 |
+
"grad_norm": 8.3125,
|
| 1233 |
+
"learning_rate": 9.456666666666667e-05,
|
| 1234 |
+
"loss": 0.8745,
|
| 1235 |
+
"step": 1490
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.1773940345368916,
|
| 1239 |
+
"grad_norm": 8.5625,
|
| 1240 |
+
"learning_rate": 9.445555555555557e-05,
|
| 1241 |
+
"loss": 1.0006,
|
| 1242 |
+
"step": 1500
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.1773940345368916,
|
| 1246 |
+
"eval/acc": 44.1860466003418,
|
| 1247 |
+
"step": 1500
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.1773940345368916,
|
| 1251 |
+
"eval_loss": 2.9012134075164795,
|
| 1252 |
+
"eval_runtime": 0.2192,
|
| 1253 |
+
"eval_samples_per_second": 196.184,
|
| 1254 |
+
"eval_steps_per_second": 4.562,
|
| 1255 |
+
"step": 1500
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.185243328100471,
|
| 1259 |
+
"grad_norm": 19.0,
|
| 1260 |
+
"learning_rate": 9.434444444444444e-05,
|
| 1261 |
+
"loss": 0.8713,
|
| 1262 |
+
"step": 1510
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.1930926216640503,
|
| 1266 |
+
"grad_norm": 9.1875,
|
| 1267 |
+
"learning_rate": 9.423333333333334e-05,
|
| 1268 |
+
"loss": 0.9389,
|
| 1269 |
+
"step": 1520
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.2009419152276295,
|
| 1273 |
+
"grad_norm": 8.0,
|
| 1274 |
+
"learning_rate": 9.412222222222222e-05,
|
| 1275 |
+
"loss": 0.8891,
|
| 1276 |
+
"step": 1530
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.2087912087912087,
|
| 1280 |
+
"grad_norm": 7.6875,
|
| 1281 |
+
"learning_rate": 9.401111111111112e-05,
|
| 1282 |
+
"loss": 0.9247,
|
| 1283 |
+
"step": 1540
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.2166405023547882,
|
| 1287 |
+
"grad_norm": 7.5,
|
| 1288 |
+
"learning_rate": 9.39e-05,
|
| 1289 |
+
"loss": 0.8403,
|
| 1290 |
+
"step": 1550
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.2244897959183674,
|
| 1294 |
+
"grad_norm": 9.75,
|
| 1295 |
+
"learning_rate": 9.378888888888889e-05,
|
| 1296 |
+
"loss": 0.8867,
|
| 1297 |
+
"step": 1560
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.2323390894819466,
|
| 1301 |
+
"grad_norm": 8.25,
|
| 1302 |
+
"learning_rate": 9.367777777777779e-05,
|
| 1303 |
+
"loss": 0.7689,
|
| 1304 |
+
"step": 1570
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.2401883830455258,
|
| 1308 |
+
"grad_norm": 10.625,
|
| 1309 |
+
"learning_rate": 9.356666666666667e-05,
|
| 1310 |
+
"loss": 0.9114,
|
| 1311 |
+
"step": 1580
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.2480376766091053,
|
| 1315 |
+
"grad_norm": 7.15625,
|
| 1316 |
+
"learning_rate": 9.345555555555556e-05,
|
| 1317 |
+
"loss": 0.8881,
|
| 1318 |
+
"step": 1590
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.2558869701726845,
|
| 1322 |
+
"grad_norm": 7.78125,
|
| 1323 |
+
"learning_rate": 9.334444444444444e-05,
|
| 1324 |
+
"loss": 0.8306,
|
| 1325 |
+
"step": 1600
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.2558869701726845,
|
| 1329 |
+
"eval/acc": 37.20930099487305,
|
| 1330 |
+
"step": 1600
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.2558869701726845,
|
| 1334 |
+
"eval_loss": 2.8547093868255615,
|
| 1335 |
+
"eval_runtime": 0.2186,
|
| 1336 |
+
"eval_samples_per_second": 196.73,
|
| 1337 |
+
"eval_steps_per_second": 4.575,
|
| 1338 |
+
"step": 1600
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 1.2637362637362637,
|
| 1342 |
+
"grad_norm": 8.5625,
|
| 1343 |
+
"learning_rate": 9.323333333333334e-05,
|
| 1344 |
+
"loss": 0.9893,
|
| 1345 |
+
"step": 1610
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 1.2715855572998431,
|
| 1349 |
+
"grad_norm": 8.625,
|
| 1350 |
+
"learning_rate": 9.312222222222223e-05,
|
| 1351 |
+
"loss": 0.7748,
|
| 1352 |
+
"step": 1620
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 1.2794348508634223,
|
| 1356 |
+
"grad_norm": 8.5,
|
| 1357 |
+
"learning_rate": 9.301111111111111e-05,
|
| 1358 |
+
"loss": 0.8694,
|
| 1359 |
+
"step": 1630
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.2872841444270016,
|
| 1363 |
+
"grad_norm": 8.25,
|
| 1364 |
+
"learning_rate": 9.290000000000001e-05,
|
| 1365 |
+
"loss": 0.8646,
|
| 1366 |
+
"step": 1640
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 1.2951334379905808,
|
| 1370 |
+
"grad_norm": 9.375,
|
| 1371 |
+
"learning_rate": 9.278888888888889e-05,
|
| 1372 |
+
"loss": 0.9928,
|
| 1373 |
+
"step": 1650
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.30298273155416,
|
| 1377 |
+
"grad_norm": 7.75,
|
| 1378 |
+
"learning_rate": 9.267777777777779e-05,
|
| 1379 |
+
"loss": 0.9459,
|
| 1380 |
+
"step": 1660
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 1.3108320251177394,
|
| 1384 |
+
"grad_norm": 7.28125,
|
| 1385 |
+
"learning_rate": 9.256666666666666e-05,
|
| 1386 |
+
"loss": 0.8749,
|
| 1387 |
+
"step": 1670
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 1.3186813186813187,
|
| 1391 |
+
"grad_norm": 11.9375,
|
| 1392 |
+
"learning_rate": 9.245555555555556e-05,
|
| 1393 |
+
"loss": 0.8305,
|
| 1394 |
+
"step": 1680
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.3265306122448979,
|
| 1398 |
+
"grad_norm": 7.375,
|
| 1399 |
+
"learning_rate": 9.234444444444445e-05,
|
| 1400 |
+
"loss": 0.8988,
|
| 1401 |
+
"step": 1690
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 1.3343799058084773,
|
| 1405 |
+
"grad_norm": 19.25,
|
| 1406 |
+
"learning_rate": 9.223333333333334e-05,
|
| 1407 |
+
"loss": 0.9189,
|
| 1408 |
+
"step": 1700
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 1.3343799058084773,
|
| 1412 |
+
"eval/acc": 39.53488540649414,
|
| 1413 |
+
"step": 1700
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.3343799058084773,
|
| 1417 |
+
"eval_loss": 3.0657997131347656,
|
| 1418 |
+
"eval_runtime": 0.2145,
|
| 1419 |
+
"eval_samples_per_second": 200.507,
|
| 1420 |
+
"eval_steps_per_second": 4.663,
|
| 1421 |
+
"step": 1700
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 1.3422291993720565,
|
| 1425 |
+
"grad_norm": 7.34375,
|
| 1426 |
+
"learning_rate": 9.212222222222223e-05,
|
| 1427 |
+
"loss": 0.9392,
|
| 1428 |
+
"step": 1710
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.3500784929356358,
|
| 1432 |
+
"grad_norm": 9.0,
|
| 1433 |
+
"learning_rate": 9.201111111111111e-05,
|
| 1434 |
+
"loss": 0.8656,
|
| 1435 |
+
"step": 1720
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 1.3579277864992152,
|
| 1439 |
+
"grad_norm": 11.1875,
|
| 1440 |
+
"learning_rate": 9.190000000000001e-05,
|
| 1441 |
+
"loss": 1.0284,
|
| 1442 |
+
"step": 1730
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.3657770800627944,
|
| 1446 |
+
"grad_norm": 7.40625,
|
| 1447 |
+
"learning_rate": 9.17888888888889e-05,
|
| 1448 |
+
"loss": 0.9395,
|
| 1449 |
+
"step": 1740
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.3736263736263736,
|
| 1453 |
+
"grad_norm": 7.0625,
|
| 1454 |
+
"learning_rate": 9.167777777777778e-05,
|
| 1455 |
+
"loss": 0.9269,
|
| 1456 |
+
"step": 1750
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.3814756671899528,
|
| 1460 |
+
"grad_norm": 9.0,
|
| 1461 |
+
"learning_rate": 9.156666666666667e-05,
|
| 1462 |
+
"loss": 0.8266,
|
| 1463 |
+
"step": 1760
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.389324960753532,
|
| 1467 |
+
"grad_norm": 7.46875,
|
| 1468 |
+
"learning_rate": 9.145555555555556e-05,
|
| 1469 |
+
"loss": 0.9045,
|
| 1470 |
+
"step": 1770
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.3971742543171115,
|
| 1474 |
+
"grad_norm": 7.25,
|
| 1475 |
+
"learning_rate": 9.134444444444445e-05,
|
| 1476 |
+
"loss": 0.9582,
|
| 1477 |
+
"step": 1780
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.4050235478806907,
|
| 1481 |
+
"grad_norm": 9.125,
|
| 1482 |
+
"learning_rate": 9.123333333333333e-05,
|
| 1483 |
+
"loss": 0.9247,
|
| 1484 |
+
"step": 1790
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.41287284144427,
|
| 1488 |
+
"grad_norm": 8.5625,
|
| 1489 |
+
"learning_rate": 9.112222222222223e-05,
|
| 1490 |
+
"loss": 0.8248,
|
| 1491 |
+
"step": 1800
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.41287284144427,
|
| 1495 |
+
"eval/acc": 41.86046600341797,
|
| 1496 |
+
"step": 1800
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 1.41287284144427,
|
| 1500 |
+
"eval_loss": 2.8882296085357666,
|
| 1501 |
+
"eval_runtime": 0.2216,
|
| 1502 |
+
"eval_samples_per_second": 194.018,
|
| 1503 |
+
"eval_steps_per_second": 4.512,
|
| 1504 |
+
"step": 1800
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 1.4207221350078494,
|
| 1508 |
+
"grad_norm": 11.3125,
|
| 1509 |
+
"learning_rate": 9.101111111111112e-05,
|
| 1510 |
+
"loss": 0.9036,
|
| 1511 |
+
"step": 1810
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 1.4285714285714286,
|
| 1515 |
+
"grad_norm": 9.5,
|
| 1516 |
+
"learning_rate": 9.090000000000001e-05,
|
| 1517 |
+
"loss": 0.8777,
|
| 1518 |
+
"step": 1820
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 1.4364207221350078,
|
| 1522 |
+
"grad_norm": 10.1875,
|
| 1523 |
+
"learning_rate": 9.078888888888889e-05,
|
| 1524 |
+
"loss": 0.9264,
|
| 1525 |
+
"step": 1830
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 1.4442700156985873,
|
| 1529 |
+
"grad_norm": 8.125,
|
| 1530 |
+
"learning_rate": 9.067777777777778e-05,
|
| 1531 |
+
"loss": 0.9161,
|
| 1532 |
+
"step": 1840
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 1.4521193092621665,
|
| 1536 |
+
"grad_norm": 11.5,
|
| 1537 |
+
"learning_rate": 9.056666666666667e-05,
|
| 1538 |
+
"loss": 0.8825,
|
| 1539 |
+
"step": 1850
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 1.4599686028257457,
|
| 1543 |
+
"grad_norm": 26.75,
|
| 1544 |
+
"learning_rate": 9.045555555555557e-05,
|
| 1545 |
+
"loss": 0.8311,
|
| 1546 |
+
"step": 1860
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.467817896389325,
|
| 1550 |
+
"grad_norm": 7.5,
|
| 1551 |
+
"learning_rate": 9.034444444444445e-05,
|
| 1552 |
+
"loss": 0.8656,
|
| 1553 |
+
"step": 1870
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 1.4756671899529041,
|
| 1557 |
+
"grad_norm": 6.34375,
|
| 1558 |
+
"learning_rate": 9.023333333333334e-05,
|
| 1559 |
+
"loss": 0.864,
|
| 1560 |
+
"step": 1880
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 1.4835164835164836,
|
| 1564 |
+
"grad_norm": 7.625,
|
| 1565 |
+
"learning_rate": 9.012222222222223e-05,
|
| 1566 |
+
"loss": 0.8694,
|
| 1567 |
+
"step": 1890
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 1.4913657770800628,
|
| 1571 |
+
"grad_norm": 8.0,
|
| 1572 |
+
"learning_rate": 9.001111111111112e-05,
|
| 1573 |
+
"loss": 0.7875,
|
| 1574 |
+
"step": 1900
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.4913657770800628,
|
| 1578 |
+
"eval/acc": 39.53488540649414,
|
| 1579 |
+
"step": 1900
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.4913657770800628,
|
| 1583 |
+
"eval_loss": 3.0755343437194824,
|
| 1584 |
+
"eval_runtime": 0.2187,
|
| 1585 |
+
"eval_samples_per_second": 196.594,
|
| 1586 |
+
"eval_steps_per_second": 4.572,
|
| 1587 |
+
"step": 1900
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 1.499215070643642,
|
| 1591 |
+
"grad_norm": 7.875,
|
| 1592 |
+
"learning_rate": 8.99e-05,
|
| 1593 |
+
"loss": 0.7767,
|
| 1594 |
+
"step": 1910
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.5070643642072215,
|
| 1598 |
+
"grad_norm": 10.75,
|
| 1599 |
+
"learning_rate": 8.978888888888889e-05,
|
| 1600 |
+
"loss": 0.8953,
|
| 1601 |
+
"step": 1920
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 1.5149136577708007,
|
| 1605 |
+
"grad_norm": 8.4375,
|
| 1606 |
+
"learning_rate": 8.967777777777779e-05,
|
| 1607 |
+
"loss": 0.8418,
|
| 1608 |
+
"step": 1930
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 1.5227629513343799,
|
| 1612 |
+
"grad_norm": 9.3125,
|
| 1613 |
+
"learning_rate": 8.956666666666667e-05,
|
| 1614 |
+
"loss": 0.8164,
|
| 1615 |
+
"step": 1940
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 1.5306122448979593,
|
| 1619 |
+
"grad_norm": 8.75,
|
| 1620 |
+
"learning_rate": 8.945555555555556e-05,
|
| 1621 |
+
"loss": 0.9608,
|
| 1622 |
+
"step": 1950
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 1.5384615384615383,
|
| 1626 |
+
"grad_norm": 9.1875,
|
| 1627 |
+
"learning_rate": 8.934444444444445e-05,
|
| 1628 |
+
"loss": 0.8257,
|
| 1629 |
+
"step": 1960
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.5463108320251178,
|
| 1633 |
+
"grad_norm": 9.875,
|
| 1634 |
+
"learning_rate": 8.923333333333334e-05,
|
| 1635 |
+
"loss": 0.8572,
|
| 1636 |
+
"step": 1970
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 1.554160125588697,
|
| 1640 |
+
"grad_norm": 10.0,
|
| 1641 |
+
"learning_rate": 8.912222222222222e-05,
|
| 1642 |
+
"loss": 0.9113,
|
| 1643 |
+
"step": 1980
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 1.5620094191522762,
|
| 1647 |
+
"grad_norm": 10.4375,
|
| 1648 |
+
"learning_rate": 8.901111111111111e-05,
|
| 1649 |
+
"loss": 0.8231,
|
| 1650 |
+
"step": 1990
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.5698587127158556,
|
| 1654 |
+
"grad_norm": 9.625,
|
| 1655 |
+
"learning_rate": 8.89e-05,
|
| 1656 |
+
"loss": 0.8652,
|
| 1657 |
+
"step": 2000
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.5698587127158556,
|
| 1661 |
+
"eval/acc": 39.53488540649414,
|
| 1662 |
+
"step": 2000
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.5698587127158556,
|
| 1666 |
+
"eval_loss": 3.079681634902954,
|
| 1667 |
+
"eval_runtime": 0.2117,
|
| 1668 |
+
"eval_samples_per_second": 203.1,
|
| 1669 |
+
"eval_steps_per_second": 4.723,
|
| 1670 |
+
"step": 2000
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 1.5777080062794349,
|
| 1674 |
+
"grad_norm": 8.0,
|
| 1675 |
+
"learning_rate": 8.878888888888889e-05,
|
| 1676 |
+
"loss": 0.8634,
|
| 1677 |
+
"step": 2010
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 1.585557299843014,
|
| 1681 |
+
"grad_norm": 8.375,
|
| 1682 |
+
"learning_rate": 8.867777777777778e-05,
|
| 1683 |
+
"loss": 0.7417,
|
| 1684 |
+
"step": 2020
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 1.5934065934065935,
|
| 1688 |
+
"grad_norm": 7.25,
|
| 1689 |
+
"learning_rate": 8.856666666666667e-05,
|
| 1690 |
+
"loss": 0.8733,
|
| 1691 |
+
"step": 2030
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 1.6012558869701727,
|
| 1695 |
+
"grad_norm": 17.0,
|
| 1696 |
+
"learning_rate": 8.845555555555556e-05,
|
| 1697 |
+
"loss": 0.9108,
|
| 1698 |
+
"step": 2040
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.609105180533752,
|
| 1702 |
+
"grad_norm": 9.1875,
|
| 1703 |
+
"learning_rate": 8.834444444444446e-05,
|
| 1704 |
+
"loss": 0.9048,
|
| 1705 |
+
"step": 2050
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 1.6169544740973314,
|
| 1709 |
+
"grad_norm": 10.25,
|
| 1710 |
+
"learning_rate": 8.823333333333334e-05,
|
| 1711 |
+
"loss": 0.8439,
|
| 1712 |
+
"step": 2060
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 1.6248037676609104,
|
| 1716 |
+
"grad_norm": 7.96875,
|
| 1717 |
+
"learning_rate": 8.812222222222223e-05,
|
| 1718 |
+
"loss": 0.9284,
|
| 1719 |
+
"step": 2070
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.6326530612244898,
|
| 1723 |
+
"grad_norm": 8.9375,
|
| 1724 |
+
"learning_rate": 8.801111111111111e-05,
|
| 1725 |
+
"loss": 0.7554,
|
| 1726 |
+
"step": 2080
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.640502354788069,
|
| 1730 |
+
"grad_norm": 8.875,
|
| 1731 |
+
"learning_rate": 8.790000000000001e-05,
|
| 1732 |
+
"loss": 0.8366,
|
| 1733 |
+
"step": 2090
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 1.6483516483516483,
|
| 1737 |
+
"grad_norm": 8.4375,
|
| 1738 |
+
"learning_rate": 8.77888888888889e-05,
|
| 1739 |
+
"loss": 0.8505,
|
| 1740 |
+
"step": 2100
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 1.6483516483516483,
|
| 1744 |
+
"eval/acc": 37.20930099487305,
|
| 1745 |
+
"step": 2100
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.6483516483516483,
|
| 1749 |
+
"eval_loss": 3.081848382949829,
|
| 1750 |
+
"eval_runtime": 0.2147,
|
| 1751 |
+
"eval_samples_per_second": 200.235,
|
| 1752 |
+
"eval_steps_per_second": 4.657,
|
| 1753 |
+
"step": 2100
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.6562009419152277,
|
| 1757 |
+
"grad_norm": 7.375,
|
| 1758 |
+
"learning_rate": 8.767777777777778e-05,
|
| 1759 |
+
"loss": 0.877,
|
| 1760 |
+
"step": 2110
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.664050235478807,
|
| 1764 |
+
"grad_norm": 9.0625,
|
| 1765 |
+
"learning_rate": 8.756666666666668e-05,
|
| 1766 |
+
"loss": 0.8486,
|
| 1767 |
+
"step": 2120
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.6718995290423861,
|
| 1771 |
+
"grad_norm": 8.5625,
|
| 1772 |
+
"learning_rate": 8.745555555555556e-05,
|
| 1773 |
+
"loss": 0.8049,
|
| 1774 |
+
"step": 2130
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.6797488226059656,
|
| 1778 |
+
"grad_norm": 8.9375,
|
| 1779 |
+
"learning_rate": 8.734444444444445e-05,
|
| 1780 |
+
"loss": 0.8756,
|
| 1781 |
+
"step": 2140
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.6875981161695446,
|
| 1785 |
+
"grad_norm": 8.75,
|
| 1786 |
+
"learning_rate": 8.723333333333333e-05,
|
| 1787 |
+
"loss": 0.9626,
|
| 1788 |
+
"step": 2150
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.695447409733124,
|
| 1792 |
+
"grad_norm": 11.3125,
|
| 1793 |
+
"learning_rate": 8.712222222222223e-05,
|
| 1794 |
+
"loss": 0.8075,
|
| 1795 |
+
"step": 2160
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.7032967032967035,
|
| 1799 |
+
"grad_norm": 8.625,
|
| 1800 |
+
"learning_rate": 8.701111111111111e-05,
|
| 1801 |
+
"loss": 0.9573,
|
| 1802 |
+
"step": 2170
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.7111459968602825,
|
| 1806 |
+
"grad_norm": 8.4375,
|
| 1807 |
+
"learning_rate": 8.69e-05,
|
| 1808 |
+
"loss": 0.9247,
|
| 1809 |
+
"step": 2180
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.718995290423862,
|
| 1813 |
+
"grad_norm": 13.0625,
|
| 1814 |
+
"learning_rate": 8.67888888888889e-05,
|
| 1815 |
+
"loss": 0.8318,
|
| 1816 |
+
"step": 2190
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.7268445839874411,
|
| 1820 |
+
"grad_norm": 7.8125,
|
| 1821 |
+
"learning_rate": 8.667777777777778e-05,
|
| 1822 |
+
"loss": 0.809,
|
| 1823 |
+
"step": 2200
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.7268445839874411,
|
| 1827 |
+
"eval/acc": 41.86046600341797,
|
| 1828 |
+
"step": 2200
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 1.7268445839874411,
|
| 1832 |
+
"eval_loss": 3.0244550704956055,
|
| 1833 |
+
"eval_runtime": 0.2186,
|
| 1834 |
+
"eval_samples_per_second": 196.676,
|
| 1835 |
+
"eval_steps_per_second": 4.574,
|
| 1836 |
+
"step": 2200
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.7346938775510203,
|
| 1840 |
+
"grad_norm": 10.0,
|
| 1841 |
+
"learning_rate": 8.656666666666668e-05,
|
| 1842 |
+
"loss": 0.7782,
|
| 1843 |
+
"step": 2210
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.7425431711145998,
|
| 1847 |
+
"grad_norm": 8.875,
|
| 1848 |
+
"learning_rate": 8.645555555555555e-05,
|
| 1849 |
+
"loss": 0.8701,
|
| 1850 |
+
"step": 2220
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.750392464678179,
|
| 1854 |
+
"grad_norm": 6.9375,
|
| 1855 |
+
"learning_rate": 8.634444444444445e-05,
|
| 1856 |
+
"loss": 0.8183,
|
| 1857 |
+
"step": 2230
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.7582417582417582,
|
| 1861 |
+
"grad_norm": 8.3125,
|
| 1862 |
+
"learning_rate": 8.623333333333333e-05,
|
| 1863 |
+
"loss": 0.8181,
|
| 1864 |
+
"step": 2240
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.7660910518053377,
|
| 1868 |
+
"grad_norm": 10.75,
|
| 1869 |
+
"learning_rate": 8.612222222222223e-05,
|
| 1870 |
+
"loss": 0.9131,
|
| 1871 |
+
"step": 2250
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.7739403453689166,
|
| 1875 |
+
"grad_norm": 8.9375,
|
| 1876 |
+
"learning_rate": 8.601111111111112e-05,
|
| 1877 |
+
"loss": 0.7837,
|
| 1878 |
+
"step": 2260
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.781789638932496,
|
| 1882 |
+
"grad_norm": 7.09375,
|
| 1883 |
+
"learning_rate": 8.59e-05,
|
| 1884 |
+
"loss": 0.8072,
|
| 1885 |
+
"step": 2270
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.7896389324960753,
|
| 1889 |
+
"grad_norm": 7.03125,
|
| 1890 |
+
"learning_rate": 8.57888888888889e-05,
|
| 1891 |
+
"loss": 0.795,
|
| 1892 |
+
"step": 2280
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.7974882260596545,
|
| 1896 |
+
"grad_norm": 9.9375,
|
| 1897 |
+
"learning_rate": 8.567777777777778e-05,
|
| 1898 |
+
"loss": 0.8375,
|
| 1899 |
+
"step": 2290
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.805337519623234,
|
| 1903 |
+
"grad_norm": 6.9375,
|
| 1904 |
+
"learning_rate": 8.556666666666667e-05,
|
| 1905 |
+
"loss": 0.8399,
|
| 1906 |
+
"step": 2300
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.805337519623234,
|
| 1910 |
+
"eval/acc": 44.1860466003418,
|
| 1911 |
+
"step": 2300
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 1.805337519623234,
|
| 1915 |
+
"eval_loss": 3.090736150741577,
|
| 1916 |
+
"eval_runtime": 0.2194,
|
| 1917 |
+
"eval_samples_per_second": 196.026,
|
| 1918 |
+
"eval_steps_per_second": 4.559,
|
| 1919 |
+
"step": 2300
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.8131868131868132,
|
| 1923 |
+
"grad_norm": 8.6875,
|
| 1924 |
+
"learning_rate": 8.545555555555555e-05,
|
| 1925 |
+
"loss": 0.8665,
|
| 1926 |
+
"step": 2310
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 1.8210361067503924,
|
| 1930 |
+
"grad_norm": 6.90625,
|
| 1931 |
+
"learning_rate": 8.534444444444445e-05,
|
| 1932 |
+
"loss": 0.8312,
|
| 1933 |
+
"step": 2320
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.8288854003139718,
|
| 1937 |
+
"grad_norm": 9.0,
|
| 1938 |
+
"learning_rate": 8.523333333333334e-05,
|
| 1939 |
+
"loss": 0.8399,
|
| 1940 |
+
"step": 2330
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 1.836734693877551,
|
| 1944 |
+
"grad_norm": 8.1875,
|
| 1945 |
+
"learning_rate": 8.512222222222222e-05,
|
| 1946 |
+
"loss": 0.8437,
|
| 1947 |
+
"step": 2340
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.8445839874411303,
|
| 1951 |
+
"grad_norm": 5.6875,
|
| 1952 |
+
"learning_rate": 8.501111111111112e-05,
|
| 1953 |
+
"loss": 0.827,
|
| 1954 |
+
"step": 2350
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 1.8524332810047097,
|
| 1958 |
+
"grad_norm": 7.34375,
|
| 1959 |
+
"learning_rate": 8.49e-05,
|
| 1960 |
+
"loss": 0.9034,
|
| 1961 |
+
"step": 2360
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.8602825745682887,
|
| 1965 |
+
"grad_norm": 9.125,
|
| 1966 |
+
"learning_rate": 8.47888888888889e-05,
|
| 1967 |
+
"loss": 0.8115,
|
| 1968 |
+
"step": 2370
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 1.8681318681318682,
|
| 1972 |
+
"grad_norm": 8.8125,
|
| 1973 |
+
"learning_rate": 8.467777777777777e-05,
|
| 1974 |
+
"loss": 0.8576,
|
| 1975 |
+
"step": 2380
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 1.8759811616954474,
|
| 1979 |
+
"grad_norm": 7.84375,
|
| 1980 |
+
"learning_rate": 8.456666666666667e-05,
|
| 1981 |
+
"loss": 0.8483,
|
| 1982 |
+
"step": 2390
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 1.8838304552590266,
|
| 1986 |
+
"grad_norm": 9.5625,
|
| 1987 |
+
"learning_rate": 8.445555555555556e-05,
|
| 1988 |
+
"loss": 0.8962,
|
| 1989 |
+
"step": 2400
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.8838304552590266,
|
| 1993 |
+
"eval/acc": 39.53488540649414,
|
| 1994 |
+
"step": 2400
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.8838304552590266,
|
| 1998 |
+
"eval_loss": 3.0378940105438232,
|
| 1999 |
+
"eval_runtime": 0.22,
|
| 2000 |
+
"eval_samples_per_second": 195.434,
|
| 2001 |
+
"eval_steps_per_second": 4.545,
|
| 2002 |
+
"step": 2400
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.891679748822606,
|
| 2006 |
+
"grad_norm": 8.1875,
|
| 2007 |
+
"learning_rate": 8.434444444444445e-05,
|
| 2008 |
+
"loss": 0.8201,
|
| 2009 |
+
"step": 2410
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 1.8995290423861853,
|
| 2013 |
+
"grad_norm": 8.5,
|
| 2014 |
+
"learning_rate": 8.423333333333334e-05,
|
| 2015 |
+
"loss": 0.916,
|
| 2016 |
+
"step": 2420
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 1.9073783359497645,
|
| 2020 |
+
"grad_norm": 8.875,
|
| 2021 |
+
"learning_rate": 8.412222222222222e-05,
|
| 2022 |
+
"loss": 0.8291,
|
| 2023 |
+
"step": 2430
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 1.915227629513344,
|
| 2027 |
+
"grad_norm": 7.09375,
|
| 2028 |
+
"learning_rate": 8.401111111111112e-05,
|
| 2029 |
+
"loss": 0.7994,
|
| 2030 |
+
"step": 2440
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 1.9230769230769231,
|
| 2034 |
+
"grad_norm": 8.25,
|
| 2035 |
+
"learning_rate": 8.39e-05,
|
| 2036 |
+
"loss": 0.8999,
|
| 2037 |
+
"step": 2450
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.9309262166405023,
|
| 2041 |
+
"grad_norm": 13.4375,
|
| 2042 |
+
"learning_rate": 8.378888888888889e-05,
|
| 2043 |
+
"loss": 0.8204,
|
| 2044 |
+
"step": 2460
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 1.9387755102040818,
|
| 2048 |
+
"grad_norm": 8.375,
|
| 2049 |
+
"learning_rate": 8.367777777777778e-05,
|
| 2050 |
+
"loss": 0.8134,
|
| 2051 |
+
"step": 2470
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 1.9466248037676608,
|
| 2055 |
+
"grad_norm": 7.5625,
|
| 2056 |
+
"learning_rate": 8.356666666666667e-05,
|
| 2057 |
+
"loss": 0.9049,
|
| 2058 |
+
"step": 2480
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.9544740973312402,
|
| 2062 |
+
"grad_norm": 6.90625,
|
| 2063 |
+
"learning_rate": 8.345555555555556e-05,
|
| 2064 |
+
"loss": 0.8928,
|
| 2065 |
+
"step": 2490
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 1.9623233908948194,
|
| 2069 |
+
"grad_norm": 7.4375,
|
| 2070 |
+
"learning_rate": 8.334444444444444e-05,
|
| 2071 |
+
"loss": 0.7481,
|
| 2072 |
+
"step": 2500
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 1.9623233908948194,
|
| 2076 |
+
"eval/acc": 39.53488540649414,
|
| 2077 |
+
"step": 2500
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 1.9623233908948194,
|
| 2081 |
+
"eval_loss": 3.135998010635376,
|
| 2082 |
+
"eval_runtime": 0.2215,
|
| 2083 |
+
"eval_samples_per_second": 194.129,
|
| 2084 |
+
"eval_steps_per_second": 4.515,
|
| 2085 |
+
"step": 2500
|
| 2086 |
+
}
|
| 2087 |
+
],
|
| 2088 |
+
"logging_steps": 10,
|
| 2089 |
+
"max_steps": 10000,
|
| 2090 |
+
"num_input_tokens_seen": 0,
|
| 2091 |
+
"num_train_epochs": 8,
|
| 2092 |
+
"save_steps": 2500,
|
| 2093 |
+
"stateful_callbacks": {
|
| 2094 |
+
"TrainerControl": {
|
| 2095 |
+
"args": {
|
| 2096 |
+
"should_epoch_stop": false,
|
| 2097 |
+
"should_evaluate": false,
|
| 2098 |
+
"should_log": false,
|
| 2099 |
+
"should_save": true,
|
| 2100 |
+
"should_training_stop": false
|
| 2101 |
+
},
|
| 2102 |
+
"attributes": {}
|
| 2103 |
+
}
|
| 2104 |
+
},
|
| 2105 |
+
"total_flos": 0.0,
|
| 2106 |
+
"train_batch_size": 16,
|
| 2107 |
+
"trial_name": null,
|
| 2108 |
+
"trial_params": null
|
| 2109 |
+
}
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2454495470a309f29bcb6e17995a0f5eba177149759169fad892e69436e76b71
|
| 3 |
+
size 6161
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000.0,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initializer_cutoff_factor": 2.0,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 1152,
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"local_attention": 128,
|
| 28 |
+
"local_rope_theta": 10000.0,
|
| 29 |
+
"max_position_embeddings": 8192,
|
| 30 |
+
"mlp_bias": false,
|
| 31 |
+
"mlp_dropout": 0.0,
|
| 32 |
+
"model_type": "modernbert",
|
| 33 |
+
"norm_bias": false,
|
| 34 |
+
"norm_eps": 1e-05,
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_hidden_layers": 22,
|
| 37 |
+
"pad_token_id": 50283,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 50282,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"transformers_version": "4.57.1",
|
| 44 |
+
"vocab_size": 50368
|
| 45 |
+
}
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26ddea10d1b592b763ee59b05f1558c3cb2f0493c1b214f3c80feb714b66c3b1
|
| 3 |
+
size 298041696
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:068adc19df70de3d48c90e1a4bfee35d3260dcecdfab93d036098987af28c762
|
| 3 |
+
size 596170443
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64751d1d30fc9a480b1be244c72d89dafe386df6d39c23a516d08b98b09ff2c0
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:149750d3cca95f5471b4108e74133b194d6009aabcc2f5743105bb4ba54b7286
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9255605ac0cd8dc1535cca4054fc8282329b95c9bfaff1e3919675dd400a0ffa
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1f5b0c4aedc1f943d8e8dc35c31e252031f0c094d6b8b7261007582209d296f
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:506f6e39bd983d811639cf9d5aea75be4643e6c5adeffc1e40a2ab6e23817ea8
|
| 3 |
+
size 1465
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-5000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2454495470a309f29bcb6e17995a0f5eba177149759169fad892e69436e76b71
|
| 3 |
+
size 6161
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000.0,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initializer_cutoff_factor": 2.0,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 1152,
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"local_attention": 128,
|
| 28 |
+
"local_rope_theta": 10000.0,
|
| 29 |
+
"max_position_embeddings": 8192,
|
| 30 |
+
"mlp_bias": false,
|
| 31 |
+
"mlp_dropout": 0.0,
|
| 32 |
+
"model_type": "modernbert",
|
| 33 |
+
"norm_bias": false,
|
| 34 |
+
"norm_eps": 1e-05,
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_hidden_layers": 22,
|
| 37 |
+
"pad_token_id": 50283,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 50282,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"transformers_version": "4.57.1",
|
| 44 |
+
"vocab_size": 50368
|
| 45 |
+
}
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4c81558929d61f7e09725cdd0299c7c9a60354e8e937058fa212bd0fed0d5dc
|
| 3 |
+
size 298041696
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aff66ee140ada517137e3deb00c2322cd5f3c5c26e947f38a24227e394683ac
|
| 3 |
+
size 596170443
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:180df0cb70bfe71e6d4e777e06e1f3a992afd71fd81bbb3480d69c4f8bcb971e
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:880b4c0d69347fd79eaf2ff1f60a002f13749950f1d35674d8f35c6f0008bb13
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5eb085b8d3eca6f4b5f8570a40562b8a87e2ffb9bc7b2144c9c9908c02824936
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16536734c942728ee2a0224fb01135653667a8c553d71c229b81bb213fd261bd
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:773947218d8d7737c8670043d737e80a30fe17375af8e46749692f7803f2df3b
|
| 3 |
+
size 1465
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/checkpoint-7500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2454495470a309f29bcb6e17995a0f5eba177149759169fad892e69436e76b71
|
| 3 |
+
size 6161
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000.0,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initializer_cutoff_factor": 2.0,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 1152,
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"local_attention": 128,
|
| 28 |
+
"local_rope_theta": 10000.0,
|
| 29 |
+
"max_position_embeddings": 8192,
|
| 30 |
+
"mlp_bias": false,
|
| 31 |
+
"mlp_dropout": 0.0,
|
| 32 |
+
"model_type": "modernbert",
|
| 33 |
+
"norm_bias": false,
|
| 34 |
+
"norm_eps": 1e-05,
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_hidden_layers": 22,
|
| 37 |
+
"pad_token_id": 50283,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 50282,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"transformers_version": "4.57.1",
|
| 44 |
+
"vocab_size": 50368
|
| 45 |
+
}
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b3f482e56a92f0760e27f700de46d09e3a07b0a89d3ef90808d0d6b22512827
|
| 3 |
+
size 298041696
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdd7dd2e666a3126c4ed005d62b97fc63ca51fad19f7d480fb83d6eac7bfbbd0
|
| 3 |
+
size 596170443
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cc940a8d556e924e63165a153482b7202c426188f75c20c24e12d424fd66480
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ffdae51287c04c7c26dda1477c56be872f0a72d6ef4c91eed718fc9815f5cd0
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a259d84200d732d2a50300986ac2bfeae195d6cd6b8a5965f25beb1168967c93
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be124d0a4382f6650d248da735663a65eb35d7e6648a020fa3373d621111b9f4
|
| 3 |
+
size 15429
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/runs/Nov24_20-04-23_nid005058/events.out.tfevents.1764007677.nid005058.100797.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:685c58b52b45168b2f278121562de91b8c14cb29067edbcdc8e998dd759b05c4
|
| 3 |
+
size 42534
|
modernbert-crux-researchy-pos_half.neg_zero.b64_n512.1e-4.512/runs/Nov24_21-15-32_nid005065/events.out.tfevents.1764011958.nid005065.96324.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:430144a74d8370489a195a9bddb6b721b9fff60644d4de8530fde0607d268ab9
|
| 3 |
+
size 254613
|