Upload folder using huggingface_hub
Browse files- outputs/base-1B/checkpoint-375/config.json +32 -0
- outputs/base-1B/checkpoint-375/generation_config.json +9 -0
- outputs/base-1B/checkpoint-375/model.safetensors +3 -0
- outputs/base-1B/checkpoint-375/optimizer.pt +3 -0
- outputs/base-1B/checkpoint-375/rng_state.pth +3 -0
- outputs/base-1B/checkpoint-375/scaler.pt +3 -0
- outputs/base-1B/checkpoint-375/scheduler.pt +3 -0
- outputs/base-1B/checkpoint-375/trainer_state.json +1343 -0
- outputs/base-1B/config.json +32 -0
- outputs/base-1B/generation_config.json +9 -0
- outputs/base-1B/model.safetensors +3 -0
outputs/base-1B/checkpoint-375/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5632,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 22,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": null,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"rope_theta": 500000.0,
|
| 26 |
+
"rope_type": "default"
|
| 27 |
+
},
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"transformers_version": "5.18.0",
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"vocab_size": 32000
|
| 32 |
+
}
|
outputs/base-1B/checkpoint-375/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"transformers_version": "5.18.0",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
outputs/base-1B/checkpoint-375/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f64fda88b04b6949958cb2c52771901ff223001f9f43632025d7e6e917cc636
|
| 3 |
+
size 4492491224
|
outputs/base-1B/checkpoint-375/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe2acfc18b16950ac31db8bc66e7f7c71be1cc3a5cb160aa5d9a7e621a57f63f
|
| 3 |
+
size 2673263115
|
outputs/base-1B/checkpoint-375/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
|
| 3 |
+
size 14645
|
outputs/base-1B/checkpoint-375/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac58ef7454dc327cdd1497d560e3c1cadc5881183c106e69fda6701af10248e8
|
| 3 |
+
size 1383
|
outputs/base-1B/checkpoint-375/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:842c9cfc377474f3cc400aa68eb12f46fcbb5333ee717560db8d34b4443de63e
|
| 3 |
+
size 1465
|
outputs/base-1B/checkpoint-375/trainer_state.json
ADDED
|
@@ -0,0 +1,1343 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 375,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016,
|
| 14 |
+
"grad_norm": 91.25221252441406,
|
| 15 |
+
"learning_rate": 0.00019946666666666667,
|
| 16 |
+
"loss": 11.301910400390625,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.032,
|
| 21 |
+
"grad_norm": 30.74045753479004,
|
| 22 |
+
"learning_rate": 0.0001984,
|
| 23 |
+
"loss": 11.70630931854248,
|
| 24 |
+
"step": 4
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.048,
|
| 28 |
+
"grad_norm": 18.54302215576172,
|
| 29 |
+
"learning_rate": 0.00019733333333333335,
|
| 30 |
+
"loss": 9.35428524017334,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.064,
|
| 35 |
+
"grad_norm": 22.490114212036133,
|
| 36 |
+
"learning_rate": 0.00019626666666666668,
|
| 37 |
+
"loss": 6.8602190017700195,
|
| 38 |
+
"step": 8
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"grad_norm": 2.945154905319214,
|
| 43 |
+
"learning_rate": 0.0001952,
|
| 44 |
+
"loss": 6.000848293304443,
|
| 45 |
+
"step": 10
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.096,
|
| 49 |
+
"grad_norm": 3.3387043476104736,
|
| 50 |
+
"learning_rate": 0.00019413333333333335,
|
| 51 |
+
"loss": 5.9754838943481445,
|
| 52 |
+
"step": 12
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.112,
|
| 56 |
+
"grad_norm": 9.287911415100098,
|
| 57 |
+
"learning_rate": 0.00019306666666666668,
|
| 58 |
+
"loss": 5.770646572113037,
|
| 59 |
+
"step": 14
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.128,
|
| 63 |
+
"grad_norm": 3.1234071254730225,
|
| 64 |
+
"learning_rate": 0.000192,
|
| 65 |
+
"loss": 5.320382118225098,
|
| 66 |
+
"step": 16
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.144,
|
| 70 |
+
"grad_norm": 2.0774896144866943,
|
| 71 |
+
"learning_rate": 0.00019093333333333333,
|
| 72 |
+
"loss": 5.7424163818359375,
|
| 73 |
+
"step": 18
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16,
|
| 77 |
+
"grad_norm": 1.6421160697937012,
|
| 78 |
+
"learning_rate": 0.00018986666666666668,
|
| 79 |
+
"loss": 5.288054943084717,
|
| 80 |
+
"step": 20
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.176,
|
| 84 |
+
"grad_norm": 2.5093605518341064,
|
| 85 |
+
"learning_rate": 0.0001888,
|
| 86 |
+
"loss": 5.4158220291137695,
|
| 87 |
+
"step": 22
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.192,
|
| 91 |
+
"grad_norm": 1.1106512546539307,
|
| 92 |
+
"learning_rate": 0.00018773333333333333,
|
| 93 |
+
"loss": 5.377811431884766,
|
| 94 |
+
"step": 24
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.208,
|
| 98 |
+
"grad_norm": 1.5716744661331177,
|
| 99 |
+
"learning_rate": 0.0001866666666666667,
|
| 100 |
+
"loss": 5.517208099365234,
|
| 101 |
+
"step": 26
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.224,
|
| 105 |
+
"grad_norm": 1.1933069229125977,
|
| 106 |
+
"learning_rate": 0.0001856,
|
| 107 |
+
"loss": 5.134151458740234,
|
| 108 |
+
"step": 28
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.24,
|
| 112 |
+
"grad_norm": 1.7340483665466309,
|
| 113 |
+
"learning_rate": 0.00018453333333333334,
|
| 114 |
+
"loss": 5.425617694854736,
|
| 115 |
+
"step": 30
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.256,
|
| 119 |
+
"grad_norm": 1.1474729776382446,
|
| 120 |
+
"learning_rate": 0.00018346666666666666,
|
| 121 |
+
"loss": 5.2034759521484375,
|
| 122 |
+
"step": 32
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.272,
|
| 126 |
+
"grad_norm": 1.079708218574524,
|
| 127 |
+
"learning_rate": 0.00018240000000000002,
|
| 128 |
+
"loss": 5.237642288208008,
|
| 129 |
+
"step": 34
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.288,
|
| 133 |
+
"grad_norm": 1.2482119798660278,
|
| 134 |
+
"learning_rate": 0.00018133333333333334,
|
| 135 |
+
"loss": 4.823528289794922,
|
| 136 |
+
"step": 36
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.304,
|
| 140 |
+
"grad_norm": 0.9924553036689758,
|
| 141 |
+
"learning_rate": 0.00018026666666666667,
|
| 142 |
+
"loss": 5.707958221435547,
|
| 143 |
+
"step": 38
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.32,
|
| 147 |
+
"grad_norm": 1.0217585563659668,
|
| 148 |
+
"learning_rate": 0.00017920000000000002,
|
| 149 |
+
"loss": 4.863388538360596,
|
| 150 |
+
"step": 40
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.336,
|
| 154 |
+
"grad_norm": 0.9102301001548767,
|
| 155 |
+
"learning_rate": 0.00017813333333333334,
|
| 156 |
+
"loss": 5.475125789642334,
|
| 157 |
+
"step": 42
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.352,
|
| 161 |
+
"grad_norm": 1.0032668113708496,
|
| 162 |
+
"learning_rate": 0.00017706666666666667,
|
| 163 |
+
"loss": 4.266422748565674,
|
| 164 |
+
"step": 44
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.368,
|
| 168 |
+
"grad_norm": 0.7802526950836182,
|
| 169 |
+
"learning_rate": 0.00017600000000000002,
|
| 170 |
+
"loss": 5.145251274108887,
|
| 171 |
+
"step": 46
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.384,
|
| 175 |
+
"grad_norm": 1.068025827407837,
|
| 176 |
+
"learning_rate": 0.00017493333333333335,
|
| 177 |
+
"loss": 5.046626091003418,
|
| 178 |
+
"step": 48
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4,
|
| 182 |
+
"grad_norm": 1.0967390537261963,
|
| 183 |
+
"learning_rate": 0.00017386666666666667,
|
| 184 |
+
"loss": 5.391576766967773,
|
| 185 |
+
"step": 50
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.416,
|
| 189 |
+
"grad_norm": 0.9503086805343628,
|
| 190 |
+
"learning_rate": 0.0001728,
|
| 191 |
+
"loss": 4.888063430786133,
|
| 192 |
+
"step": 52
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.432,
|
| 196 |
+
"grad_norm": 1.1517038345336914,
|
| 197 |
+
"learning_rate": 0.00017173333333333335,
|
| 198 |
+
"loss": 5.384998798370361,
|
| 199 |
+
"step": 54
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.448,
|
| 203 |
+
"grad_norm": 1.9094752073287964,
|
| 204 |
+
"learning_rate": 0.00017066666666666668,
|
| 205 |
+
"loss": 5.498985767364502,
|
| 206 |
+
"step": 56
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.464,
|
| 210 |
+
"grad_norm": 1.1735854148864746,
|
| 211 |
+
"learning_rate": 0.0001696,
|
| 212 |
+
"loss": 5.007707118988037,
|
| 213 |
+
"step": 58
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"grad_norm": 1.1846449375152588,
|
| 218 |
+
"learning_rate": 0.00016853333333333336,
|
| 219 |
+
"loss": 5.221414566040039,
|
| 220 |
+
"step": 60
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.496,
|
| 224 |
+
"grad_norm": 1.1998226642608643,
|
| 225 |
+
"learning_rate": 0.00016746666666666668,
|
| 226 |
+
"loss": 5.543745517730713,
|
| 227 |
+
"step": 62
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.512,
|
| 231 |
+
"grad_norm": 0.8612433075904846,
|
| 232 |
+
"learning_rate": 0.0001664,
|
| 233 |
+
"loss": 4.801937580108643,
|
| 234 |
+
"step": 64
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.528,
|
| 238 |
+
"grad_norm": 0.8453647494316101,
|
| 239 |
+
"learning_rate": 0.00016533333333333333,
|
| 240 |
+
"loss": 4.524555206298828,
|
| 241 |
+
"step": 66
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.544,
|
| 245 |
+
"grad_norm": 1.1736576557159424,
|
| 246 |
+
"learning_rate": 0.00016426666666666668,
|
| 247 |
+
"loss": 4.566590309143066,
|
| 248 |
+
"step": 68
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"grad_norm": 1.0967543125152588,
|
| 253 |
+
"learning_rate": 0.0001632,
|
| 254 |
+
"loss": 4.3014373779296875,
|
| 255 |
+
"step": 70
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.576,
|
| 259 |
+
"grad_norm": 1.0685675144195557,
|
| 260 |
+
"learning_rate": 0.00016213333333333334,
|
| 261 |
+
"loss": 4.867293834686279,
|
| 262 |
+
"step": 72
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.592,
|
| 266 |
+
"grad_norm": 1.0959752798080444,
|
| 267 |
+
"learning_rate": 0.0001610666666666667,
|
| 268 |
+
"loss": 4.832211971282959,
|
| 269 |
+
"step": 74
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.608,
|
| 273 |
+
"grad_norm": 1.0644458532333374,
|
| 274 |
+
"learning_rate": 0.00016,
|
| 275 |
+
"loss": 5.169826984405518,
|
| 276 |
+
"step": 76
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.624,
|
| 280 |
+
"grad_norm": 0.8699787855148315,
|
| 281 |
+
"learning_rate": 0.00015893333333333334,
|
| 282 |
+
"loss": 4.778270244598389,
|
| 283 |
+
"step": 78
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.64,
|
| 287 |
+
"grad_norm": 1.368355393409729,
|
| 288 |
+
"learning_rate": 0.00015786666666666666,
|
| 289 |
+
"loss": 5.334726333618164,
|
| 290 |
+
"step": 80
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.656,
|
| 294 |
+
"grad_norm": 1.1871856451034546,
|
| 295 |
+
"learning_rate": 0.00015680000000000002,
|
| 296 |
+
"loss": 5.064769744873047,
|
| 297 |
+
"step": 82
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.672,
|
| 301 |
+
"grad_norm": 1.3017299175262451,
|
| 302 |
+
"learning_rate": 0.00015573333333333334,
|
| 303 |
+
"loss": 4.902538299560547,
|
| 304 |
+
"step": 84
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.688,
|
| 308 |
+
"grad_norm": 1.0173554420471191,
|
| 309 |
+
"learning_rate": 0.00015466666666666667,
|
| 310 |
+
"loss": 4.402043342590332,
|
| 311 |
+
"step": 86
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.704,
|
| 315 |
+
"grad_norm": 0.935325562953949,
|
| 316 |
+
"learning_rate": 0.00015360000000000002,
|
| 317 |
+
"loss": 4.725499629974365,
|
| 318 |
+
"step": 88
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.72,
|
| 322 |
+
"grad_norm": 1.540722131729126,
|
| 323 |
+
"learning_rate": 0.00015253333333333335,
|
| 324 |
+
"loss": 5.1958818435668945,
|
| 325 |
+
"step": 90
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.736,
|
| 329 |
+
"grad_norm": 0.941829264163971,
|
| 330 |
+
"learning_rate": 0.00015146666666666667,
|
| 331 |
+
"loss": 5.109292507171631,
|
| 332 |
+
"step": 92
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.752,
|
| 336 |
+
"grad_norm": 0.8813519477844238,
|
| 337 |
+
"learning_rate": 0.0001504,
|
| 338 |
+
"loss": 4.460155010223389,
|
| 339 |
+
"step": 94
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.768,
|
| 343 |
+
"grad_norm": 0.9416606426239014,
|
| 344 |
+
"learning_rate": 0.00014933333333333335,
|
| 345 |
+
"loss": 4.7534966468811035,
|
| 346 |
+
"step": 96
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.784,
|
| 350 |
+
"grad_norm": 0.9442281126976013,
|
| 351 |
+
"learning_rate": 0.00014826666666666667,
|
| 352 |
+
"loss": 4.644475936889648,
|
| 353 |
+
"step": 98
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8,
|
| 357 |
+
"grad_norm": 0.7593088746070862,
|
| 358 |
+
"learning_rate": 0.0001472,
|
| 359 |
+
"loss": 4.6469268798828125,
|
| 360 |
+
"step": 100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.816,
|
| 364 |
+
"grad_norm": 0.8361356854438782,
|
| 365 |
+
"learning_rate": 0.00014613333333333335,
|
| 366 |
+
"loss": 4.576081275939941,
|
| 367 |
+
"step": 102
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.832,
|
| 371 |
+
"grad_norm": 0.8503762483596802,
|
| 372 |
+
"learning_rate": 0.00014506666666666668,
|
| 373 |
+
"loss": 4.950436115264893,
|
| 374 |
+
"step": 104
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.848,
|
| 378 |
+
"grad_norm": 0.8762472867965698,
|
| 379 |
+
"learning_rate": 0.000144,
|
| 380 |
+
"loss": 4.586020469665527,
|
| 381 |
+
"step": 106
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.864,
|
| 385 |
+
"grad_norm": 1.1207101345062256,
|
| 386 |
+
"learning_rate": 0.00014293333333333333,
|
| 387 |
+
"loss": 4.6015753746032715,
|
| 388 |
+
"step": 108
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.88,
|
| 392 |
+
"grad_norm": 0.9852073788642883,
|
| 393 |
+
"learning_rate": 0.00014186666666666668,
|
| 394 |
+
"loss": 4.285760402679443,
|
| 395 |
+
"step": 110
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.896,
|
| 399 |
+
"grad_norm": 1.0251927375793457,
|
| 400 |
+
"learning_rate": 0.0001408,
|
| 401 |
+
"loss": 3.922407388687134,
|
| 402 |
+
"step": 112
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.912,
|
| 406 |
+
"grad_norm": 0.9398831129074097,
|
| 407 |
+
"learning_rate": 0.00013973333333333333,
|
| 408 |
+
"loss": 4.907520294189453,
|
| 409 |
+
"step": 114
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.928,
|
| 413 |
+
"grad_norm": 0.9326450228691101,
|
| 414 |
+
"learning_rate": 0.00013866666666666669,
|
| 415 |
+
"loss": 4.532372951507568,
|
| 416 |
+
"step": 116
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.944,
|
| 420 |
+
"grad_norm": 0.9748089909553528,
|
| 421 |
+
"learning_rate": 0.00013759999999999998,
|
| 422 |
+
"loss": 4.431105136871338,
|
| 423 |
+
"step": 118
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.96,
|
| 427 |
+
"grad_norm": 0.9428505897521973,
|
| 428 |
+
"learning_rate": 0.00013653333333333334,
|
| 429 |
+
"loss": 4.470233917236328,
|
| 430 |
+
"step": 120
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.976,
|
| 434 |
+
"grad_norm": 0.6841837167739868,
|
| 435 |
+
"learning_rate": 0.00013546666666666666,
|
| 436 |
+
"loss": 3.7584588527679443,
|
| 437 |
+
"step": 122
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.992,
|
| 441 |
+
"grad_norm": 0.8173671364784241,
|
| 442 |
+
"learning_rate": 0.00013440000000000001,
|
| 443 |
+
"loss": 4.330744743347168,
|
| 444 |
+
"step": 124
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.008,
|
| 448 |
+
"grad_norm": 0.8738037347793579,
|
| 449 |
+
"learning_rate": 0.00013333333333333334,
|
| 450 |
+
"loss": 4.579251289367676,
|
| 451 |
+
"step": 126
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.024,
|
| 455 |
+
"grad_norm": 1.1318062543869019,
|
| 456 |
+
"learning_rate": 0.00013226666666666667,
|
| 457 |
+
"loss": 4.669555187225342,
|
| 458 |
+
"step": 128
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.04,
|
| 462 |
+
"grad_norm": 1.0786882638931274,
|
| 463 |
+
"learning_rate": 0.00013120000000000002,
|
| 464 |
+
"loss": 3.935119152069092,
|
| 465 |
+
"step": 130
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.056,
|
| 469 |
+
"grad_norm": 0.9966052770614624,
|
| 470 |
+
"learning_rate": 0.00013013333333333332,
|
| 471 |
+
"loss": 4.3407440185546875,
|
| 472 |
+
"step": 132
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.072,
|
| 476 |
+
"grad_norm": 0.7376568913459778,
|
| 477 |
+
"learning_rate": 0.00012906666666666667,
|
| 478 |
+
"loss": 4.275925159454346,
|
| 479 |
+
"step": 134
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.088,
|
| 483 |
+
"grad_norm": 0.8541952967643738,
|
| 484 |
+
"learning_rate": 0.00012800000000000002,
|
| 485 |
+
"loss": 4.15697717666626,
|
| 486 |
+
"step": 136
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.104,
|
| 490 |
+
"grad_norm": 1.0582785606384277,
|
| 491 |
+
"learning_rate": 0.00012693333333333335,
|
| 492 |
+
"loss": 4.362380504608154,
|
| 493 |
+
"step": 138
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.12,
|
| 497 |
+
"grad_norm": 0.9308528900146484,
|
| 498 |
+
"learning_rate": 0.00012586666666666667,
|
| 499 |
+
"loss": 4.672689437866211,
|
| 500 |
+
"step": 140
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.1360000000000001,
|
| 504 |
+
"grad_norm": 0.88565593957901,
|
| 505 |
+
"learning_rate": 0.0001248,
|
| 506 |
+
"loss": 4.076122760772705,
|
| 507 |
+
"step": 142
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.152,
|
| 511 |
+
"grad_norm": 0.9385479092597961,
|
| 512 |
+
"learning_rate": 0.00012373333333333335,
|
| 513 |
+
"loss": 4.161294937133789,
|
| 514 |
+
"step": 144
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.168,
|
| 518 |
+
"grad_norm": 0.8026373982429504,
|
| 519 |
+
"learning_rate": 0.00012266666666666668,
|
| 520 |
+
"loss": 4.3729753494262695,
|
| 521 |
+
"step": 146
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.184,
|
| 525 |
+
"grad_norm": 0.7829592823982239,
|
| 526 |
+
"learning_rate": 0.0001216,
|
| 527 |
+
"loss": 4.2869157791137695,
|
| 528 |
+
"step": 148
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.2,
|
| 532 |
+
"grad_norm": 0.7095411419868469,
|
| 533 |
+
"learning_rate": 0.00012053333333333334,
|
| 534 |
+
"loss": 4.605996608734131,
|
| 535 |
+
"step": 150
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.216,
|
| 539 |
+
"grad_norm": 0.7309772372245789,
|
| 540 |
+
"learning_rate": 0.00011946666666666668,
|
| 541 |
+
"loss": 3.9801695346832275,
|
| 542 |
+
"step": 152
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.232,
|
| 546 |
+
"grad_norm": 0.8839707970619202,
|
| 547 |
+
"learning_rate": 0.0001184,
|
| 548 |
+
"loss": 4.390212059020996,
|
| 549 |
+
"step": 154
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.248,
|
| 553 |
+
"grad_norm": 0.8657903075218201,
|
| 554 |
+
"learning_rate": 0.00011733333333333334,
|
| 555 |
+
"loss": 3.741997718811035,
|
| 556 |
+
"step": 156
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.264,
|
| 560 |
+
"grad_norm": 0.8276820182800293,
|
| 561 |
+
"learning_rate": 0.00011626666666666668,
|
| 562 |
+
"loss": 4.154025554656982,
|
| 563 |
+
"step": 158
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.28,
|
| 567 |
+
"grad_norm": 0.8782942891120911,
|
| 568 |
+
"learning_rate": 0.0001152,
|
| 569 |
+
"loss": 4.225947856903076,
|
| 570 |
+
"step": 160
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.296,
|
| 574 |
+
"grad_norm": 0.7055423259735107,
|
| 575 |
+
"learning_rate": 0.00011413333333333333,
|
| 576 |
+
"loss": 4.264814853668213,
|
| 577 |
+
"step": 162
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.312,
|
| 581 |
+
"grad_norm": 1.018231749534607,
|
| 582 |
+
"learning_rate": 0.00011306666666666667,
|
| 583 |
+
"loss": 4.483643054962158,
|
| 584 |
+
"step": 164
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.328,
|
| 588 |
+
"grad_norm": 1.0415221452713013,
|
| 589 |
+
"learning_rate": 0.00011200000000000001,
|
| 590 |
+
"loss": 4.67912483215332,
|
| 591 |
+
"step": 166
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.3439999999999999,
|
| 595 |
+
"grad_norm": 0.7224927544593811,
|
| 596 |
+
"learning_rate": 0.00011093333333333334,
|
| 597 |
+
"loss": 3.911421775817871,
|
| 598 |
+
"step": 168
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.3599999999999999,
|
| 602 |
+
"grad_norm": 0.7978851795196533,
|
| 603 |
+
"learning_rate": 0.00010986666666666668,
|
| 604 |
+
"loss": 4.311194896697998,
|
| 605 |
+
"step": 170
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.376,
|
| 609 |
+
"grad_norm": 0.715904176235199,
|
| 610 |
+
"learning_rate": 0.00010880000000000002,
|
| 611 |
+
"loss": 4.041537284851074,
|
| 612 |
+
"step": 172
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.392,
|
| 616 |
+
"grad_norm": 0.8608409762382507,
|
| 617 |
+
"learning_rate": 0.00010773333333333333,
|
| 618 |
+
"loss": 4.377121448516846,
|
| 619 |
+
"step": 174
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.408,
|
| 623 |
+
"grad_norm": 0.8278133869171143,
|
| 624 |
+
"learning_rate": 0.00010666666666666667,
|
| 625 |
+
"loss": 4.022895812988281,
|
| 626 |
+
"step": 176
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.424,
|
| 630 |
+
"grad_norm": 0.7697980999946594,
|
| 631 |
+
"learning_rate": 0.0001056,
|
| 632 |
+
"loss": 3.8939197063446045,
|
| 633 |
+
"step": 178
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.44,
|
| 637 |
+
"grad_norm": 0.8733091950416565,
|
| 638 |
+
"learning_rate": 0.00010453333333333333,
|
| 639 |
+
"loss": 4.316196918487549,
|
| 640 |
+
"step": 180
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.456,
|
| 644 |
+
"grad_norm": 0.6546777486801147,
|
| 645 |
+
"learning_rate": 0.00010346666666666667,
|
| 646 |
+
"loss": 3.761678695678711,
|
| 647 |
+
"step": 182
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.472,
|
| 651 |
+
"grad_norm": 0.8486815690994263,
|
| 652 |
+
"learning_rate": 0.00010240000000000001,
|
| 653 |
+
"loss": 4.615560054779053,
|
| 654 |
+
"step": 184
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.488,
|
| 658 |
+
"grad_norm": 0.7845205664634705,
|
| 659 |
+
"learning_rate": 0.00010133333333333335,
|
| 660 |
+
"loss": 4.1724748611450195,
|
| 661 |
+
"step": 186
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.504,
|
| 665 |
+
"grad_norm": 0.7691537737846375,
|
| 666 |
+
"learning_rate": 0.00010026666666666666,
|
| 667 |
+
"loss": 4.03464412689209,
|
| 668 |
+
"step": 188
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.52,
|
| 672 |
+
"grad_norm": 0.6386341452598572,
|
| 673 |
+
"learning_rate": 9.92e-05,
|
| 674 |
+
"loss": 3.817345142364502,
|
| 675 |
+
"step": 190
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.536,
|
| 679 |
+
"grad_norm": 0.837395966053009,
|
| 680 |
+
"learning_rate": 9.813333333333334e-05,
|
| 681 |
+
"loss": 4.165748596191406,
|
| 682 |
+
"step": 192
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.552,
|
| 686 |
+
"grad_norm": 0.9616137742996216,
|
| 687 |
+
"learning_rate": 9.706666666666668e-05,
|
| 688 |
+
"loss": 3.7803008556365967,
|
| 689 |
+
"step": 194
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.568,
|
| 693 |
+
"grad_norm": 0.7027558088302612,
|
| 694 |
+
"learning_rate": 9.6e-05,
|
| 695 |
+
"loss": 3.643509864807129,
|
| 696 |
+
"step": 196
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.584,
|
| 700 |
+
"grad_norm": 0.7428299784660339,
|
| 701 |
+
"learning_rate": 9.493333333333334e-05,
|
| 702 |
+
"loss": 4.098444938659668,
|
| 703 |
+
"step": 198
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.6,
|
| 707 |
+
"grad_norm": 0.660114586353302,
|
| 708 |
+
"learning_rate": 9.386666666666667e-05,
|
| 709 |
+
"loss": 3.8980801105499268,
|
| 710 |
+
"step": 200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.616,
|
| 714 |
+
"grad_norm": 0.6948791146278381,
|
| 715 |
+
"learning_rate": 9.28e-05,
|
| 716 |
+
"loss": 3.9728848934173584,
|
| 717 |
+
"step": 202
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.6320000000000001,
|
| 721 |
+
"grad_norm": 0.7276217341423035,
|
| 722 |
+
"learning_rate": 9.173333333333333e-05,
|
| 723 |
+
"loss": 4.23557710647583,
|
| 724 |
+
"step": 204
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.6480000000000001,
|
| 728 |
+
"grad_norm": 0.7324399352073669,
|
| 729 |
+
"learning_rate": 9.066666666666667e-05,
|
| 730 |
+
"loss": 4.105298042297363,
|
| 731 |
+
"step": 206
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.6640000000000001,
|
| 735 |
+
"grad_norm": 0.8022691011428833,
|
| 736 |
+
"learning_rate": 8.960000000000001e-05,
|
| 737 |
+
"loss": 4.346144676208496,
|
| 738 |
+
"step": 208
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.6800000000000002,
|
| 742 |
+
"grad_norm": 0.8563399910926819,
|
| 743 |
+
"learning_rate": 8.853333333333333e-05,
|
| 744 |
+
"loss": 4.4715166091918945,
|
| 745 |
+
"step": 210
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.696,
|
| 749 |
+
"grad_norm": 0.7636263966560364,
|
| 750 |
+
"learning_rate": 8.746666666666667e-05,
|
| 751 |
+
"loss": 4.136549949645996,
|
| 752 |
+
"step": 212
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.712,
|
| 756 |
+
"grad_norm": 0.7314817905426025,
|
| 757 |
+
"learning_rate": 8.64e-05,
|
| 758 |
+
"loss": 3.470980167388916,
|
| 759 |
+
"step": 214
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.728,
|
| 763 |
+
"grad_norm": 0.7136172652244568,
|
| 764 |
+
"learning_rate": 8.533333333333334e-05,
|
| 765 |
+
"loss": 4.124269485473633,
|
| 766 |
+
"step": 216
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.744,
|
| 770 |
+
"grad_norm": 0.6093188524246216,
|
| 771 |
+
"learning_rate": 8.426666666666668e-05,
|
| 772 |
+
"loss": 3.7720394134521484,
|
| 773 |
+
"step": 218
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.76,
|
| 777 |
+
"grad_norm": 0.8954075574874878,
|
| 778 |
+
"learning_rate": 8.32e-05,
|
| 779 |
+
"loss": 4.447854042053223,
|
| 780 |
+
"step": 220
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.776,
|
| 784 |
+
"grad_norm": 0.7287309169769287,
|
| 785 |
+
"learning_rate": 8.213333333333334e-05,
|
| 786 |
+
"loss": 3.939310073852539,
|
| 787 |
+
"step": 222
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.792,
|
| 791 |
+
"grad_norm": 0.7149838209152222,
|
| 792 |
+
"learning_rate": 8.106666666666667e-05,
|
| 793 |
+
"loss": 4.298111438751221,
|
| 794 |
+
"step": 224
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.808,
|
| 798 |
+
"grad_norm": 0.6960682272911072,
|
| 799 |
+
"learning_rate": 8e-05,
|
| 800 |
+
"loss": 3.8210666179656982,
|
| 801 |
+
"step": 226
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.8239999999999998,
|
| 805 |
+
"grad_norm": 0.8319933414459229,
|
| 806 |
+
"learning_rate": 7.893333333333333e-05,
|
| 807 |
+
"loss": 4.475030422210693,
|
| 808 |
+
"step": 228
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.8399999999999999,
|
| 812 |
+
"grad_norm": 0.8333290815353394,
|
| 813 |
+
"learning_rate": 7.786666666666667e-05,
|
| 814 |
+
"loss": 3.932643413543701,
|
| 815 |
+
"step": 230
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.8559999999999999,
|
| 819 |
+
"grad_norm": 0.9156264066696167,
|
| 820 |
+
"learning_rate": 7.680000000000001e-05,
|
| 821 |
+
"loss": 4.079849720001221,
|
| 822 |
+
"step": 232
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.8719999999999999,
|
| 826 |
+
"grad_norm": 0.7633479833602905,
|
| 827 |
+
"learning_rate": 7.573333333333334e-05,
|
| 828 |
+
"loss": 4.2749104499816895,
|
| 829 |
+
"step": 234
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.888,
|
| 833 |
+
"grad_norm": 0.7579272389411926,
|
| 834 |
+
"learning_rate": 7.466666666666667e-05,
|
| 835 |
+
"loss": 4.346074104309082,
|
| 836 |
+
"step": 236
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.904,
|
| 840 |
+
"grad_norm": 0.973507285118103,
|
| 841 |
+
"learning_rate": 7.36e-05,
|
| 842 |
+
"loss": 4.377317905426025,
|
| 843 |
+
"step": 238
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.92,
|
| 847 |
+
"grad_norm": 0.6797956824302673,
|
| 848 |
+
"learning_rate": 7.253333333333334e-05,
|
| 849 |
+
"loss": 3.85811710357666,
|
| 850 |
+
"step": 240
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.936,
|
| 854 |
+
"grad_norm": 0.6061505675315857,
|
| 855 |
+
"learning_rate": 7.146666666666666e-05,
|
| 856 |
+
"loss": 3.5419416427612305,
|
| 857 |
+
"step": 242
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.952,
|
| 861 |
+
"grad_norm": 0.7688581943511963,
|
| 862 |
+
"learning_rate": 7.04e-05,
|
| 863 |
+
"loss": 4.2483391761779785,
|
| 864 |
+
"step": 244
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.968,
|
| 868 |
+
"grad_norm": 0.8147947192192078,
|
| 869 |
+
"learning_rate": 6.933333333333334e-05,
|
| 870 |
+
"loss": 4.273576736450195,
|
| 871 |
+
"step": 246
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.984,
|
| 875 |
+
"grad_norm": 0.6104022264480591,
|
| 876 |
+
"learning_rate": 6.826666666666667e-05,
|
| 877 |
+
"loss": 3.484281301498413,
|
| 878 |
+
"step": 248
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.0,
|
| 882 |
+
"grad_norm": 0.7732232809066772,
|
| 883 |
+
"learning_rate": 6.720000000000001e-05,
|
| 884 |
+
"loss": 3.2377171516418457,
|
| 885 |
+
"step": 250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.016,
|
| 889 |
+
"grad_norm": 0.762334406375885,
|
| 890 |
+
"learning_rate": 6.613333333333333e-05,
|
| 891 |
+
"loss": 3.5851635932922363,
|
| 892 |
+
"step": 252
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.032,
|
| 896 |
+
"grad_norm": 0.9944146871566772,
|
| 897 |
+
"learning_rate": 6.506666666666666e-05,
|
| 898 |
+
"loss": 3.974273681640625,
|
| 899 |
+
"step": 254
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.048,
|
| 903 |
+
"grad_norm": 0.7827261090278625,
|
| 904 |
+
"learning_rate": 6.400000000000001e-05,
|
| 905 |
+
"loss": 3.7628493309020996,
|
| 906 |
+
"step": 256
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.064,
|
| 910 |
+
"grad_norm": 0.87816321849823,
|
| 911 |
+
"learning_rate": 6.293333333333334e-05,
|
| 912 |
+
"loss": 4.076901435852051,
|
| 913 |
+
"step": 258
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.08,
|
| 917 |
+
"grad_norm": 0.8127502799034119,
|
| 918 |
+
"learning_rate": 6.186666666666668e-05,
|
| 919 |
+
"loss": 3.75767183303833,
|
| 920 |
+
"step": 260
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.096,
|
| 924 |
+
"grad_norm": 0.7041977643966675,
|
| 925 |
+
"learning_rate": 6.08e-05,
|
| 926 |
+
"loss": 3.6286160945892334,
|
| 927 |
+
"step": 262
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.112,
|
| 931 |
+
"grad_norm": 0.7007743716239929,
|
| 932 |
+
"learning_rate": 5.973333333333334e-05,
|
| 933 |
+
"loss": 3.8136487007141113,
|
| 934 |
+
"step": 264
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.128,
|
| 938 |
+
"grad_norm": 0.9205703735351562,
|
| 939 |
+
"learning_rate": 5.866666666666667e-05,
|
| 940 |
+
"loss": 4.26763391494751,
|
| 941 |
+
"step": 266
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.144,
|
| 945 |
+
"grad_norm": 0.5952937602996826,
|
| 946 |
+
"learning_rate": 5.76e-05,
|
| 947 |
+
"loss": 3.3517656326293945,
|
| 948 |
+
"step": 268
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.16,
|
| 952 |
+
"grad_norm": 0.7217035293579102,
|
| 953 |
+
"learning_rate": 5.6533333333333336e-05,
|
| 954 |
+
"loss": 3.936736583709717,
|
| 955 |
+
"step": 270
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.176,
|
| 959 |
+
"grad_norm": 0.7669926285743713,
|
| 960 |
+
"learning_rate": 5.546666666666667e-05,
|
| 961 |
+
"loss": 3.665748119354248,
|
| 962 |
+
"step": 272
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.192,
|
| 966 |
+
"grad_norm": 0.7839015126228333,
|
| 967 |
+
"learning_rate": 5.440000000000001e-05,
|
| 968 |
+
"loss": 3.41610050201416,
|
| 969 |
+
"step": 274
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.208,
|
| 973 |
+
"grad_norm": 0.6732955574989319,
|
| 974 |
+
"learning_rate": 5.333333333333333e-05,
|
| 975 |
+
"loss": 3.6392323970794678,
|
| 976 |
+
"step": 276
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.224,
|
| 980 |
+
"grad_norm": 0.7496451735496521,
|
| 981 |
+
"learning_rate": 5.2266666666666665e-05,
|
| 982 |
+
"loss": 3.8274030685424805,
|
| 983 |
+
"step": 278
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.24,
|
| 987 |
+
"grad_norm": 0.7629424333572388,
|
| 988 |
+
"learning_rate": 5.1200000000000004e-05,
|
| 989 |
+
"loss": 3.6851420402526855,
|
| 990 |
+
"step": 280
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.2560000000000002,
|
| 994 |
+
"grad_norm": 0.7672740817070007,
|
| 995 |
+
"learning_rate": 5.013333333333333e-05,
|
| 996 |
+
"loss": 3.449460029602051,
|
| 997 |
+
"step": 282
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.2720000000000002,
|
| 1001 |
+
"grad_norm": 0.6511777639389038,
|
| 1002 |
+
"learning_rate": 4.906666666666667e-05,
|
| 1003 |
+
"loss": 3.8724024295806885,
|
| 1004 |
+
"step": 284
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.288,
|
| 1008 |
+
"grad_norm": 0.7679948806762695,
|
| 1009 |
+
"learning_rate": 4.8e-05,
|
| 1010 |
+
"loss": 4.2019944190979,
|
| 1011 |
+
"step": 286
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.304,
|
| 1015 |
+
"grad_norm": 0.6437345743179321,
|
| 1016 |
+
"learning_rate": 4.6933333333333333e-05,
|
| 1017 |
+
"loss": 3.4552133083343506,
|
| 1018 |
+
"step": 288
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.32,
|
| 1022 |
+
"grad_norm": 0.611971378326416,
|
| 1023 |
+
"learning_rate": 4.5866666666666666e-05,
|
| 1024 |
+
"loss": 3.864457845687866,
|
| 1025 |
+
"step": 290
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.336,
|
| 1029 |
+
"grad_norm": 0.9200534224510193,
|
| 1030 |
+
"learning_rate": 4.4800000000000005e-05,
|
| 1031 |
+
"loss": 4.489575386047363,
|
| 1032 |
+
"step": 292
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.352,
|
| 1036 |
+
"grad_norm": 0.686712384223938,
|
| 1037 |
+
"learning_rate": 4.373333333333334e-05,
|
| 1038 |
+
"loss": 3.947661876678467,
|
| 1039 |
+
"step": 294
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.368,
|
| 1043 |
+
"grad_norm": 0.7409478425979614,
|
| 1044 |
+
"learning_rate": 4.266666666666667e-05,
|
| 1045 |
+
"loss": 3.774221897125244,
|
| 1046 |
+
"step": 296
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.384,
|
| 1050 |
+
"grad_norm": 0.805950403213501,
|
| 1051 |
+
"learning_rate": 4.16e-05,
|
| 1052 |
+
"loss": 3.863893985748291,
|
| 1053 |
+
"step": 298
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.4,
|
| 1057 |
+
"grad_norm": 0.7230635285377502,
|
| 1058 |
+
"learning_rate": 4.0533333333333334e-05,
|
| 1059 |
+
"loss": 3.46525502204895,
|
| 1060 |
+
"step": 300
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.416,
|
| 1064 |
+
"grad_norm": 0.5924413204193115,
|
| 1065 |
+
"learning_rate": 3.9466666666666666e-05,
|
| 1066 |
+
"loss": 3.2000229358673096,
|
| 1067 |
+
"step": 302
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.432,
|
| 1071 |
+
"grad_norm": 0.6821393966674805,
|
| 1072 |
+
"learning_rate": 3.8400000000000005e-05,
|
| 1073 |
+
"loss": 3.905883312225342,
|
| 1074 |
+
"step": 304
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.448,
|
| 1078 |
+
"grad_norm": 0.7838084697723389,
|
| 1079 |
+
"learning_rate": 3.733333333333334e-05,
|
| 1080 |
+
"loss": 3.8095669746398926,
|
| 1081 |
+
"step": 306
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.464,
|
| 1085 |
+
"grad_norm": 0.6165845394134521,
|
| 1086 |
+
"learning_rate": 3.626666666666667e-05,
|
| 1087 |
+
"loss": 3.4089715480804443,
|
| 1088 |
+
"step": 308
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.48,
|
| 1092 |
+
"grad_norm": 0.6887221336364746,
|
| 1093 |
+
"learning_rate": 3.52e-05,
|
| 1094 |
+
"loss": 3.584824800491333,
|
| 1095 |
+
"step": 310
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.496,
|
| 1099 |
+
"grad_norm": 0.6511623859405518,
|
| 1100 |
+
"learning_rate": 3.4133333333333334e-05,
|
| 1101 |
+
"loss": 3.4640514850616455,
|
| 1102 |
+
"step": 312
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.512,
|
| 1106 |
+
"grad_norm": 0.6095097661018372,
|
| 1107 |
+
"learning_rate": 3.3066666666666666e-05,
|
| 1108 |
+
"loss": 3.5366129875183105,
|
| 1109 |
+
"step": 314
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.528,
|
| 1113 |
+
"grad_norm": 0.8535370826721191,
|
| 1114 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 1115 |
+
"loss": 3.5104854106903076,
|
| 1116 |
+
"step": 316
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.544,
|
| 1120 |
+
"grad_norm": 0.7049218416213989,
|
| 1121 |
+
"learning_rate": 3.093333333333334e-05,
|
| 1122 |
+
"loss": 3.7805652618408203,
|
| 1123 |
+
"step": 318
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.56,
|
| 1127 |
+
"grad_norm": 0.686198353767395,
|
| 1128 |
+
"learning_rate": 2.986666666666667e-05,
|
| 1129 |
+
"loss": 3.758275032043457,
|
| 1130 |
+
"step": 320
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.576,
|
| 1134 |
+
"grad_norm": 0.6875713467597961,
|
| 1135 |
+
"learning_rate": 2.88e-05,
|
| 1136 |
+
"loss": 3.433825969696045,
|
| 1137 |
+
"step": 322
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.592,
|
| 1141 |
+
"grad_norm": 0.6404330730438232,
|
| 1142 |
+
"learning_rate": 2.7733333333333334e-05,
|
| 1143 |
+
"loss": 3.86714768409729,
|
| 1144 |
+
"step": 324
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.608,
|
| 1148 |
+
"grad_norm": 0.6015328168869019,
|
| 1149 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 1150 |
+
"loss": 3.4464452266693115,
|
| 1151 |
+
"step": 326
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.624,
|
| 1155 |
+
"grad_norm": 0.6744190454483032,
|
| 1156 |
+
"learning_rate": 2.5600000000000002e-05,
|
| 1157 |
+
"loss": 3.487985610961914,
|
| 1158 |
+
"step": 328
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.64,
|
| 1162 |
+
"grad_norm": 0.6818214058876038,
|
| 1163 |
+
"learning_rate": 2.4533333333333334e-05,
|
| 1164 |
+
"loss": 4.076210021972656,
|
| 1165 |
+
"step": 330
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.656,
|
| 1169 |
+
"grad_norm": 0.6208036541938782,
|
| 1170 |
+
"learning_rate": 2.3466666666666667e-05,
|
| 1171 |
+
"loss": 3.627427816390991,
|
| 1172 |
+
"step": 332
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.672,
|
| 1176 |
+
"grad_norm": 0.6891155242919922,
|
| 1177 |
+
"learning_rate": 2.2400000000000002e-05,
|
| 1178 |
+
"loss": 3.6860899925231934,
|
| 1179 |
+
"step": 334
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.6879999999999997,
|
| 1183 |
+
"grad_norm": 0.5982719659805298,
|
| 1184 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 1185 |
+
"loss": 3.6903350353240967,
|
| 1186 |
+
"step": 336
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.7039999999999997,
|
| 1190 |
+
"grad_norm": 0.6474561095237732,
|
| 1191 |
+
"learning_rate": 2.0266666666666667e-05,
|
| 1192 |
+
"loss": 3.372323989868164,
|
| 1193 |
+
"step": 338
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.7199999999999998,
|
| 1197 |
+
"grad_norm": 0.6456882953643799,
|
| 1198 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 1199 |
+
"loss": 4.0264177322387695,
|
| 1200 |
+
"step": 340
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.7359999999999998,
|
| 1204 |
+
"grad_norm": 0.715237557888031,
|
| 1205 |
+
"learning_rate": 1.8133333333333335e-05,
|
| 1206 |
+
"loss": 3.9498841762542725,
|
| 1207 |
+
"step": 342
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.752,
|
| 1211 |
+
"grad_norm": 0.6222976446151733,
|
| 1212 |
+
"learning_rate": 1.7066666666666667e-05,
|
| 1213 |
+
"loss": 3.705057144165039,
|
| 1214 |
+
"step": 344
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.768,
|
| 1218 |
+
"grad_norm": 0.7751534581184387,
|
| 1219 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 1220 |
+
"loss": 3.9404139518737793,
|
| 1221 |
+
"step": 346
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.784,
|
| 1225 |
+
"grad_norm": 0.7131832838058472,
|
| 1226 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 1227 |
+
"loss": 3.5828709602355957,
|
| 1228 |
+
"step": 348
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.8,
|
| 1232 |
+
"grad_norm": 0.5506916642189026,
|
| 1233 |
+
"learning_rate": 1.3866666666666667e-05,
|
| 1234 |
+
"loss": 2.974977493286133,
|
| 1235 |
+
"step": 350
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.816,
|
| 1239 |
+
"grad_norm": 0.6306346654891968,
|
| 1240 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 1241 |
+
"loss": 3.662637710571289,
|
| 1242 |
+
"step": 352
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.832,
|
| 1246 |
+
"grad_norm": 0.7092022895812988,
|
| 1247 |
+
"learning_rate": 1.1733333333333333e-05,
|
| 1248 |
+
"loss": 3.5085391998291016,
|
| 1249 |
+
"step": 354
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.848,
|
| 1253 |
+
"grad_norm": 0.6482096314430237,
|
| 1254 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 1255 |
+
"loss": 3.857386827468872,
|
| 1256 |
+
"step": 356
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.864,
|
| 1260 |
+
"grad_norm": 0.5598263740539551,
|
| 1261 |
+
"learning_rate": 9.600000000000001e-06,
|
| 1262 |
+
"loss": 3.0743608474731445,
|
| 1263 |
+
"step": 358
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.88,
|
| 1267 |
+
"grad_norm": 0.6144701242446899,
|
| 1268 |
+
"learning_rate": 8.533333333333334e-06,
|
| 1269 |
+
"loss": 3.905026435852051,
|
| 1270 |
+
"step": 360
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.896,
|
| 1274 |
+
"grad_norm": 0.6015005707740784,
|
| 1275 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 1276 |
+
"loss": 3.2578914165496826,
|
| 1277 |
+
"step": 362
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.912,
|
| 1281 |
+
"grad_norm": 0.5701616406440735,
|
| 1282 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 1283 |
+
"loss": 3.4835946559906006,
|
| 1284 |
+
"step": 364
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.928,
|
| 1288 |
+
"grad_norm": 0.5824424028396606,
|
| 1289 |
+
"learning_rate": 5.333333333333334e-06,
|
| 1290 |
+
"loss": 3.3783047199249268,
|
| 1291 |
+
"step": 366
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.944,
|
| 1295 |
+
"grad_norm": 0.6300989985466003,
|
| 1296 |
+
"learning_rate": 4.266666666666667e-06,
|
| 1297 |
+
"loss": 3.344311475753784,
|
| 1298 |
+
"step": 368
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.96,
|
| 1302 |
+
"grad_norm": 0.6221782565116882,
|
| 1303 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 1304 |
+
"loss": 3.6499929428100586,
|
| 1305 |
+
"step": 370
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.976,
|
| 1309 |
+
"grad_norm": 0.5832206010818481,
|
| 1310 |
+
"learning_rate": 2.1333333333333334e-06,
|
| 1311 |
+
"loss": 3.1643853187561035,
|
| 1312 |
+
"step": 372
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.992,
|
| 1316 |
+
"grad_norm": 0.619193434715271,
|
| 1317 |
+
"learning_rate": 1.0666666666666667e-06,
|
| 1318 |
+
"loss": 3.8058221340179443,
|
| 1319 |
+
"step": 374
|
| 1320 |
+
}
|
| 1321 |
+
],
|
| 1322 |
+
"logging_steps": 2,
|
| 1323 |
+
"max_steps": 375,
|
| 1324 |
+
"num_input_tokens_seen": 0,
|
| 1325 |
+
"num_train_epochs": 3,
|
| 1326 |
+
"save_steps": 50,
|
| 1327 |
+
"stateful_callbacks": {
|
| 1328 |
+
"TrainerControl": {
|
| 1329 |
+
"args": {
|
| 1330 |
+
"should_epoch_stop": false,
|
| 1331 |
+
"should_evaluate": false,
|
| 1332 |
+
"should_log": false,
|
| 1333 |
+
"should_save": true,
|
| 1334 |
+
"should_training_stop": true
|
| 1335 |
+
},
|
| 1336 |
+
"attributes": {}
|
| 1337 |
+
}
|
| 1338 |
+
},
|
| 1339 |
+
"total_flos": 3.8986668048384e+16,
|
| 1340 |
+
"train_batch_size": 1,
|
| 1341 |
+
"trial_name": null,
|
| 1342 |
+
"trial_params": null
|
| 1343 |
+
}
|
outputs/base-1B/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5632,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 22,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": null,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"rope_theta": 500000.0,
|
| 26 |
+
"rope_type": "default"
|
| 27 |
+
},
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"transformers_version": "5.18.0",
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"vocab_size": 32000
|
| 32 |
+
}
|
outputs/base-1B/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"transformers_version": "5.18.0",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
outputs/base-1B/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f64fda88b04b6949958cb2c52771901ff223001f9f43632025d7e6e917cc636
|
| 3 |
+
size 4492491224
|