Upload folder using huggingface_hub
Browse files- config.json +58 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3263 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Lfm2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"block_auto_adjust_ff_dim": true,
|
| 6 |
+
"block_dim": 2048,
|
| 7 |
+
"block_ff_dim": 12288,
|
| 8 |
+
"block_ffn_dim_multiplier": 1.0,
|
| 9 |
+
"block_mlp_init_scale": 1.0,
|
| 10 |
+
"block_multiple_of": 256,
|
| 11 |
+
"block_norm_eps": 1e-05,
|
| 12 |
+
"block_out_init_scale": 1.0,
|
| 13 |
+
"block_use_swiglu": true,
|
| 14 |
+
"block_use_xavier_init": true,
|
| 15 |
+
"bos_token_id": 1,
|
| 16 |
+
"conv_L_cache": 3,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": 2048,
|
| 19 |
+
"conv_use_xavier_init": true,
|
| 20 |
+
"dtype": "bfloat16",
|
| 21 |
+
"eos_token_id": 7,
|
| 22 |
+
"hidden_size": 2048,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 12288,
|
| 25 |
+
"layer_types": [
|
| 26 |
+
"conv",
|
| 27 |
+
"conv",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"conv",
|
| 30 |
+
"conv",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"conv",
|
| 33 |
+
"conv",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"conv",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"conv",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"conv",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"conv"
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 128000,
|
| 44 |
+
"model_type": "lfm2",
|
| 45 |
+
"norm_eps": 1e-05,
|
| 46 |
+
"num_attention_heads": 32,
|
| 47 |
+
"num_heads": 32,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"output_hidden_states": true,
|
| 51 |
+
"pad_token_id": 0,
|
| 52 |
+
"rope_theta": 1000000.0,
|
| 53 |
+
"tie_embedding": true,
|
| 54 |
+
"transformers_version": "4.57.3",
|
| 55 |
+
"use_cache": true,
|
| 56 |
+
"use_pos_enc": true,
|
| 57 |
+
"vocab_size": 65536
|
| 58 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:950e2b6d52795741bf917ba3ede9bf88c91be0f8f29132c3bae8907d9f54361d
|
| 3 |
+
size 4681573135
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce6417d7584496cf384207663a7807933899ce1e023c9f5bbc2ad0330359ea23
|
| 3 |
+
size 2340784443
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42c959958db0ac952e0b543b0706d5dcc92e0dabd3917896b0e12836545d4a27
|
| 3 |
+
size 1465
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3263 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.12569217985154357,
|
| 6 |
+
"eval_steps": 501,
|
| 7 |
+
"global_step": 4500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 2.793159552256524e-05,
|
| 14 |
+
"grad_norm": 37.485023498535156,
|
| 15 |
+
"learning_rate": 2e-06,
|
| 16 |
+
"loss": 2.1306,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00027931595522565235,
|
| 21 |
+
"grad_norm": 27.45977210998535,
|
| 22 |
+
"learning_rate": 1.9994972347913524e-06,
|
| 23 |
+
"loss": 2.0875,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0005586319104513047,
|
| 28 |
+
"grad_norm": 18.15777015686035,
|
| 29 |
+
"learning_rate": 1.998938606781744e-06,
|
| 30 |
+
"loss": 1.9196,
|
| 31 |
+
"step": 20
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0008379478656769571,
|
| 35 |
+
"grad_norm": 20.21579360961914,
|
| 36 |
+
"learning_rate": 1.9983799787721355e-06,
|
| 37 |
+
"loss": 1.8183,
|
| 38 |
+
"step": 30
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0011172638209026094,
|
| 42 |
+
"grad_norm": 14.037498474121094,
|
| 43 |
+
"learning_rate": 1.9978213507625273e-06,
|
| 44 |
+
"loss": 1.7441,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.001396579776128262,
|
| 49 |
+
"grad_norm": 13.131041526794434,
|
| 50 |
+
"learning_rate": 1.9972627227529187e-06,
|
| 51 |
+
"loss": 1.6705,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0016758957313539142,
|
| 56 |
+
"grad_norm": 14.493760108947754,
|
| 57 |
+
"learning_rate": 1.99670409474331e-06,
|
| 58 |
+
"loss": 1.7261,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0019552116865795667,
|
| 63 |
+
"grad_norm": 15.630404472351074,
|
| 64 |
+
"learning_rate": 1.996145466733702e-06,
|
| 65 |
+
"loss": 1.7375,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.002234527641805219,
|
| 70 |
+
"grad_norm": 12.822752952575684,
|
| 71 |
+
"learning_rate": 1.9955868387240936e-06,
|
| 72 |
+
"loss": 1.6683,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0025138435970308713,
|
| 77 |
+
"grad_norm": 12.364542961120605,
|
| 78 |
+
"learning_rate": 1.995028210714485e-06,
|
| 79 |
+
"loss": 1.5954,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.002793159552256524,
|
| 84 |
+
"grad_norm": 14.236380577087402,
|
| 85 |
+
"learning_rate": 1.994469582704877e-06,
|
| 86 |
+
"loss": 1.6029,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0030724755074821764,
|
| 91 |
+
"grad_norm": 13.032842636108398,
|
| 92 |
+
"learning_rate": 1.9939109546952686e-06,
|
| 93 |
+
"loss": 1.6026,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0033517914627078284,
|
| 98 |
+
"grad_norm": 14.683618545532227,
|
| 99 |
+
"learning_rate": 1.99335232668566e-06,
|
| 100 |
+
"loss": 1.6354,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.003631107417933481,
|
| 105 |
+
"grad_norm": 12.228134155273438,
|
| 106 |
+
"learning_rate": 1.9927936986760517e-06,
|
| 107 |
+
"loss": 1.5176,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.0039104233731591335,
|
| 112 |
+
"grad_norm": 14.089844703674316,
|
| 113 |
+
"learning_rate": 1.992235070666443e-06,
|
| 114 |
+
"loss": 1.5644,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.004189739328384786,
|
| 119 |
+
"grad_norm": 13.192647933959961,
|
| 120 |
+
"learning_rate": 1.9916764426568345e-06,
|
| 121 |
+
"loss": 1.6016,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.004469055283610438,
|
| 126 |
+
"grad_norm": 13.630595207214355,
|
| 127 |
+
"learning_rate": 1.9911178146472263e-06,
|
| 128 |
+
"loss": 1.5195,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.00474837123883609,
|
| 133 |
+
"grad_norm": 12.795489311218262,
|
| 134 |
+
"learning_rate": 1.990559186637618e-06,
|
| 135 |
+
"loss": 1.4888,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.005027687194061743,
|
| 140 |
+
"grad_norm": 14.711332321166992,
|
| 141 |
+
"learning_rate": 1.9900005586280094e-06,
|
| 142 |
+
"loss": 1.4658,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.005307003149287395,
|
| 147 |
+
"grad_norm": 14.496808052062988,
|
| 148 |
+
"learning_rate": 1.989441930618401e-06,
|
| 149 |
+
"loss": 1.5231,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.005586319104513048,
|
| 154 |
+
"grad_norm": 11.26836109161377,
|
| 155 |
+
"learning_rate": 1.988883302608793e-06,
|
| 156 |
+
"loss": 1.3865,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.0058656350597387,
|
| 161 |
+
"grad_norm": 12.824557304382324,
|
| 162 |
+
"learning_rate": 1.9883246745991844e-06,
|
| 163 |
+
"loss": 1.4743,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.006144951014964353,
|
| 168 |
+
"grad_norm": 13.50056266784668,
|
| 169 |
+
"learning_rate": 1.9877660465895757e-06,
|
| 170 |
+
"loss": 1.3856,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.006424266970190004,
|
| 175 |
+
"grad_norm": 12.35004997253418,
|
| 176 |
+
"learning_rate": 1.9872074185799675e-06,
|
| 177 |
+
"loss": 1.4165,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.006703582925415657,
|
| 182 |
+
"grad_norm": 11.969117164611816,
|
| 183 |
+
"learning_rate": 1.986648790570359e-06,
|
| 184 |
+
"loss": 1.3719,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.006982898880641309,
|
| 189 |
+
"grad_norm": 12.795903205871582,
|
| 190 |
+
"learning_rate": 1.9860901625607507e-06,
|
| 191 |
+
"loss": 1.4586,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.007262214835866962,
|
| 196 |
+
"grad_norm": 14.326574325561523,
|
| 197 |
+
"learning_rate": 1.9855315345511424e-06,
|
| 198 |
+
"loss": 1.4185,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.0075415307910926144,
|
| 203 |
+
"grad_norm": 14.065360069274902,
|
| 204 |
+
"learning_rate": 1.984972906541534e-06,
|
| 205 |
+
"loss": 1.3441,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.007820846746318267,
|
| 210 |
+
"grad_norm": 13.229423522949219,
|
| 211 |
+
"learning_rate": 1.9844142785319256e-06,
|
| 212 |
+
"loss": 1.4299,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.00810016270154392,
|
| 217 |
+
"grad_norm": 10.81311321258545,
|
| 218 |
+
"learning_rate": 1.9838556505223174e-06,
|
| 219 |
+
"loss": 1.4352,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.008379478656769572,
|
| 224 |
+
"grad_norm": 11.971837043762207,
|
| 225 |
+
"learning_rate": 1.9832970225127088e-06,
|
| 226 |
+
"loss": 1.3721,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.008658794611995225,
|
| 231 |
+
"grad_norm": 10.858203887939453,
|
| 232 |
+
"learning_rate": 1.9827383945031e-06,
|
| 233 |
+
"loss": 1.3593,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.008938110567220875,
|
| 238 |
+
"grad_norm": 13.713777542114258,
|
| 239 |
+
"learning_rate": 1.982179766493492e-06,
|
| 240 |
+
"loss": 1.3732,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.009217426522446528,
|
| 245 |
+
"grad_norm": 10.59002685546875,
|
| 246 |
+
"learning_rate": 1.9816211384838833e-06,
|
| 247 |
+
"loss": 1.3841,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.00949674247767218,
|
| 252 |
+
"grad_norm": 12.030527114868164,
|
| 253 |
+
"learning_rate": 1.981062510474275e-06,
|
| 254 |
+
"loss": 1.3584,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.009776058432897833,
|
| 259 |
+
"grad_norm": 13.677680969238281,
|
| 260 |
+
"learning_rate": 1.980503882464667e-06,
|
| 261 |
+
"loss": 1.3468,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.010055374388123485,
|
| 266 |
+
"grad_norm": 11.954497337341309,
|
| 267 |
+
"learning_rate": 1.9799452544550582e-06,
|
| 268 |
+
"loss": 1.3558,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.010334690343349138,
|
| 273 |
+
"grad_norm": 11.743765830993652,
|
| 274 |
+
"learning_rate": 1.97938662644545e-06,
|
| 275 |
+
"loss": 1.33,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.01061400629857479,
|
| 280 |
+
"grad_norm": 14.092965126037598,
|
| 281 |
+
"learning_rate": 1.978827998435842e-06,
|
| 282 |
+
"loss": 1.3247,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.010893322253800443,
|
| 287 |
+
"grad_norm": 12.351668357849121,
|
| 288 |
+
"learning_rate": 1.978269370426233e-06,
|
| 289 |
+
"loss": 1.359,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.011172638209026095,
|
| 294 |
+
"grad_norm": 12.778825759887695,
|
| 295 |
+
"learning_rate": 1.9777107424166245e-06,
|
| 296 |
+
"loss": 1.3317,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.011451954164251748,
|
| 301 |
+
"grad_norm": 13.161787986755371,
|
| 302 |
+
"learning_rate": 1.9771521144070163e-06,
|
| 303 |
+
"loss": 1.3726,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.0117312701194774,
|
| 308 |
+
"grad_norm": 12.683723449707031,
|
| 309 |
+
"learning_rate": 1.9765934863974077e-06,
|
| 310 |
+
"loss": 1.2869,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.012010586074703053,
|
| 315 |
+
"grad_norm": 11.430862426757812,
|
| 316 |
+
"learning_rate": 1.9760348583877995e-06,
|
| 317 |
+
"loss": 1.3741,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.012289902029928705,
|
| 322 |
+
"grad_norm": 12.193629264831543,
|
| 323 |
+
"learning_rate": 1.9754762303781913e-06,
|
| 324 |
+
"loss": 1.3247,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.012569217985154356,
|
| 329 |
+
"grad_norm": 12.044336318969727,
|
| 330 |
+
"learning_rate": 1.9749176023685826e-06,
|
| 331 |
+
"loss": 1.3258,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.012848533940380009,
|
| 336 |
+
"grad_norm": 13.162397384643555,
|
| 337 |
+
"learning_rate": 1.9743589743589744e-06,
|
| 338 |
+
"loss": 1.3035,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.013127849895605661,
|
| 343 |
+
"grad_norm": 13.332141876220703,
|
| 344 |
+
"learning_rate": 1.9738003463493658e-06,
|
| 345 |
+
"loss": 1.2725,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.013407165850831314,
|
| 350 |
+
"grad_norm": 11.433170318603516,
|
| 351 |
+
"learning_rate": 1.9732417183397576e-06,
|
| 352 |
+
"loss": 1.293,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.013686481806056966,
|
| 357 |
+
"grad_norm": 11.537554740905762,
|
| 358 |
+
"learning_rate": 1.972683090330149e-06,
|
| 359 |
+
"loss": 1.3865,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.013965797761282619,
|
| 364 |
+
"grad_norm": 13.405438423156738,
|
| 365 |
+
"learning_rate": 1.9721244623205407e-06,
|
| 366 |
+
"loss": 1.3675,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.013993729356805184,
|
| 371 |
+
"eval_complexity_accuracy": 0.0,
|
| 372 |
+
"eval_loss": 1.3878909349441528,
|
| 373 |
+
"eval_runtime": 33.2902,
|
| 374 |
+
"eval_samples_per_second": 15.019,
|
| 375 |
+
"eval_steps_per_second": 1.892,
|
| 376 |
+
"step": 501
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.014245113716508271,
|
| 380 |
+
"grad_norm": 13.519207000732422,
|
| 381 |
+
"learning_rate": 1.971565834310932e-06,
|
| 382 |
+
"loss": 1.2924,
|
| 383 |
+
"step": 510
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.014524429671733924,
|
| 387 |
+
"grad_norm": 12.743926048278809,
|
| 388 |
+
"learning_rate": 1.971007206301324e-06,
|
| 389 |
+
"loss": 1.3396,
|
| 390 |
+
"step": 520
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.014803745626959576,
|
| 394 |
+
"grad_norm": 11.494955062866211,
|
| 395 |
+
"learning_rate": 1.9704485782917157e-06,
|
| 396 |
+
"loss": 1.3783,
|
| 397 |
+
"step": 530
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.015083061582185229,
|
| 401 |
+
"grad_norm": 13.423910140991211,
|
| 402 |
+
"learning_rate": 1.969889950282107e-06,
|
| 403 |
+
"loss": 1.3687,
|
| 404 |
+
"step": 540
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.015362377537410881,
|
| 408 |
+
"grad_norm": 12.793667793273926,
|
| 409 |
+
"learning_rate": 1.969331322272499e-06,
|
| 410 |
+
"loss": 1.3364,
|
| 411 |
+
"step": 550
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.015641693492636534,
|
| 415 |
+
"grad_norm": 12.060896873474121,
|
| 416 |
+
"learning_rate": 1.96877269426289e-06,
|
| 417 |
+
"loss": 1.3495,
|
| 418 |
+
"step": 560
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.015921009447862185,
|
| 422 |
+
"grad_norm": 10.879355430603027,
|
| 423 |
+
"learning_rate": 1.968214066253282e-06,
|
| 424 |
+
"loss": 1.2966,
|
| 425 |
+
"step": 570
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.01620032540308784,
|
| 429 |
+
"grad_norm": 11.109333038330078,
|
| 430 |
+
"learning_rate": 1.9676554382436733e-06,
|
| 431 |
+
"loss": 1.3587,
|
| 432 |
+
"step": 580
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.01647964135831349,
|
| 436 |
+
"grad_norm": 14.08962345123291,
|
| 437 |
+
"learning_rate": 1.967096810234065e-06,
|
| 438 |
+
"loss": 1.3881,
|
| 439 |
+
"step": 590
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.016758957313539144,
|
| 443 |
+
"grad_norm": 13.27667236328125,
|
| 444 |
+
"learning_rate": 1.9665381822244565e-06,
|
| 445 |
+
"loss": 1.3097,
|
| 446 |
+
"step": 600
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.017038273268764795,
|
| 450 |
+
"grad_norm": 11.379706382751465,
|
| 451 |
+
"learning_rate": 1.9659795542148483e-06,
|
| 452 |
+
"loss": 1.305,
|
| 453 |
+
"step": 610
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.01731758922399045,
|
| 457 |
+
"grad_norm": 12.25299072265625,
|
| 458 |
+
"learning_rate": 1.96542092620524e-06,
|
| 459 |
+
"loss": 1.3136,
|
| 460 |
+
"step": 620
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.0175969051792161,
|
| 464 |
+
"grad_norm": 11.619131088256836,
|
| 465 |
+
"learning_rate": 1.9648622981956314e-06,
|
| 466 |
+
"loss": 1.3265,
|
| 467 |
+
"step": 630
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.01787622113444175,
|
| 471 |
+
"grad_norm": 13.470244407653809,
|
| 472 |
+
"learning_rate": 1.9643036701860228e-06,
|
| 473 |
+
"loss": 1.3938,
|
| 474 |
+
"step": 640
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.018155537089667405,
|
| 478 |
+
"grad_norm": 12.438233375549316,
|
| 479 |
+
"learning_rate": 1.9637450421764146e-06,
|
| 480 |
+
"loss": 1.3579,
|
| 481 |
+
"step": 650
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.018434853044893056,
|
| 485 |
+
"grad_norm": 11.806841850280762,
|
| 486 |
+
"learning_rate": 1.9631864141668064e-06,
|
| 487 |
+
"loss": 1.3165,
|
| 488 |
+
"step": 660
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.01871416900011871,
|
| 492 |
+
"grad_norm": 10.943819999694824,
|
| 493 |
+
"learning_rate": 1.9626277861571977e-06,
|
| 494 |
+
"loss": 1.3435,
|
| 495 |
+
"step": 670
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.01899348495534436,
|
| 499 |
+
"grad_norm": 11.002156257629395,
|
| 500 |
+
"learning_rate": 1.9620691581475895e-06,
|
| 501 |
+
"loss": 1.3137,
|
| 502 |
+
"step": 680
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.019272800910570015,
|
| 506 |
+
"grad_norm": 11.192991256713867,
|
| 507 |
+
"learning_rate": 1.961510530137981e-06,
|
| 508 |
+
"loss": 1.341,
|
| 509 |
+
"step": 690
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.019552116865795666,
|
| 513 |
+
"grad_norm": 11.328652381896973,
|
| 514 |
+
"learning_rate": 1.9609519021283727e-06,
|
| 515 |
+
"loss": 1.3744,
|
| 516 |
+
"step": 700
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.01983143282102132,
|
| 520 |
+
"grad_norm": 11.382583618164062,
|
| 521 |
+
"learning_rate": 1.9603932741187645e-06,
|
| 522 |
+
"loss": 1.2749,
|
| 523 |
+
"step": 710
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.02011074877624697,
|
| 527 |
+
"grad_norm": 9.765230178833008,
|
| 528 |
+
"learning_rate": 1.959834646109156e-06,
|
| 529 |
+
"loss": 1.3148,
|
| 530 |
+
"step": 720
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.020390064731472625,
|
| 534 |
+
"grad_norm": 10.793863296508789,
|
| 535 |
+
"learning_rate": 1.959276018099547e-06,
|
| 536 |
+
"loss": 1.2991,
|
| 537 |
+
"step": 730
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.020669380686698276,
|
| 541 |
+
"grad_norm": 12.697861671447754,
|
| 542 |
+
"learning_rate": 1.958717390089939e-06,
|
| 543 |
+
"loss": 1.3673,
|
| 544 |
+
"step": 740
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.02094869664192393,
|
| 548 |
+
"grad_norm": 11.78731632232666,
|
| 549 |
+
"learning_rate": 1.9581587620803308e-06,
|
| 550 |
+
"loss": 1.36,
|
| 551 |
+
"step": 750
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.02122801259714958,
|
| 555 |
+
"grad_norm": 11.723365783691406,
|
| 556 |
+
"learning_rate": 1.957600134070722e-06,
|
| 557 |
+
"loss": 1.3558,
|
| 558 |
+
"step": 760
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.02150732855237523,
|
| 562 |
+
"grad_norm": 11.155319213867188,
|
| 563 |
+
"learning_rate": 1.957041506061114e-06,
|
| 564 |
+
"loss": 1.3266,
|
| 565 |
+
"step": 770
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.021786644507600886,
|
| 569 |
+
"grad_norm": 11.003241539001465,
|
| 570 |
+
"learning_rate": 1.9564828780515053e-06,
|
| 571 |
+
"loss": 1.3161,
|
| 572 |
+
"step": 780
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.022065960462826537,
|
| 576 |
+
"grad_norm": 11.691163063049316,
|
| 577 |
+
"learning_rate": 1.955924250041897e-06,
|
| 578 |
+
"loss": 1.3782,
|
| 579 |
+
"step": 790
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.02234527641805219,
|
| 583 |
+
"grad_norm": 13.002456665039062,
|
| 584 |
+
"learning_rate": 1.955365622032289e-06,
|
| 585 |
+
"loss": 1.3738,
|
| 586 |
+
"step": 800
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.02262459237327784,
|
| 590 |
+
"grad_norm": 10.829326629638672,
|
| 591 |
+
"learning_rate": 1.9548069940226802e-06,
|
| 592 |
+
"loss": 1.3089,
|
| 593 |
+
"step": 810
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.022903908328503496,
|
| 597 |
+
"grad_norm": 11.259895324707031,
|
| 598 |
+
"learning_rate": 1.9542483660130716e-06,
|
| 599 |
+
"loss": 1.3002,
|
| 600 |
+
"step": 820
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.023183224283729147,
|
| 604 |
+
"grad_norm": 12.811477661132812,
|
| 605 |
+
"learning_rate": 1.9536897380034634e-06,
|
| 606 |
+
"loss": 1.3126,
|
| 607 |
+
"step": 830
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.0234625402389548,
|
| 611 |
+
"grad_norm": 11.347965240478516,
|
| 612 |
+
"learning_rate": 1.953131109993855e-06,
|
| 613 |
+
"loss": 1.3364,
|
| 614 |
+
"step": 840
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.02374185619418045,
|
| 618 |
+
"grad_norm": 12.316996574401855,
|
| 619 |
+
"learning_rate": 1.9525724819842465e-06,
|
| 620 |
+
"loss": 1.3208,
|
| 621 |
+
"step": 850
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.024021172149406106,
|
| 625 |
+
"grad_norm": 11.446920394897461,
|
| 626 |
+
"learning_rate": 1.9520138539746383e-06,
|
| 627 |
+
"loss": 1.3292,
|
| 628 |
+
"step": 860
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.024300488104631757,
|
| 632 |
+
"grad_norm": 11.28432559967041,
|
| 633 |
+
"learning_rate": 1.9514552259650297e-06,
|
| 634 |
+
"loss": 1.3331,
|
| 635 |
+
"step": 870
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.02457980405985741,
|
| 639 |
+
"grad_norm": 11.215639114379883,
|
| 640 |
+
"learning_rate": 1.9508965979554215e-06,
|
| 641 |
+
"loss": 1.3026,
|
| 642 |
+
"step": 880
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.02485912001508306,
|
| 646 |
+
"grad_norm": 11.234190940856934,
|
| 647 |
+
"learning_rate": 1.950337969945813e-06,
|
| 648 |
+
"loss": 1.2926,
|
| 649 |
+
"step": 890
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.025138435970308712,
|
| 653 |
+
"grad_norm": 11.294180870056152,
|
| 654 |
+
"learning_rate": 1.9497793419362046e-06,
|
| 655 |
+
"loss": 1.3644,
|
| 656 |
+
"step": 900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.025417751925534367,
|
| 660 |
+
"grad_norm": 11.346322059631348,
|
| 661 |
+
"learning_rate": 1.949220713926596e-06,
|
| 662 |
+
"loss": 1.3124,
|
| 663 |
+
"step": 910
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.025697067880760018,
|
| 667 |
+
"grad_norm": 11.497020721435547,
|
| 668 |
+
"learning_rate": 1.9486620859169878e-06,
|
| 669 |
+
"loss": 1.2695,
|
| 670 |
+
"step": 920
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.025976383835985672,
|
| 674 |
+
"grad_norm": 10.896917343139648,
|
| 675 |
+
"learning_rate": 1.9481034579073796e-06,
|
| 676 |
+
"loss": 1.3141,
|
| 677 |
+
"step": 930
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.026255699791211323,
|
| 681 |
+
"grad_norm": 10.956721305847168,
|
| 682 |
+
"learning_rate": 1.947544829897771e-06,
|
| 683 |
+
"loss": 1.36,
|
| 684 |
+
"step": 940
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.026535015746436977,
|
| 688 |
+
"grad_norm": 11.796623229980469,
|
| 689 |
+
"learning_rate": 1.9469862018881627e-06,
|
| 690 |
+
"loss": 1.3586,
|
| 691 |
+
"step": 950
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.026814331701662628,
|
| 695 |
+
"grad_norm": 11.082508087158203,
|
| 696 |
+
"learning_rate": 1.946427573878554e-06,
|
| 697 |
+
"loss": 1.3514,
|
| 698 |
+
"step": 960
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.027093647656888282,
|
| 702 |
+
"grad_norm": 11.789264678955078,
|
| 703 |
+
"learning_rate": 1.945868945868946e-06,
|
| 704 |
+
"loss": 1.328,
|
| 705 |
+
"step": 970
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.027372963612113933,
|
| 709 |
+
"grad_norm": 11.333861351013184,
|
| 710 |
+
"learning_rate": 1.9453103178593372e-06,
|
| 711 |
+
"loss": 1.2765,
|
| 712 |
+
"step": 980
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.027652279567339587,
|
| 716 |
+
"grad_norm": 12.05320930480957,
|
| 717 |
+
"learning_rate": 1.944751689849729e-06,
|
| 718 |
+
"loss": 1.3679,
|
| 719 |
+
"step": 990
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.027931595522565238,
|
| 723 |
+
"grad_norm": 12.946321487426758,
|
| 724 |
+
"learning_rate": 1.9441930618401204e-06,
|
| 725 |
+
"loss": 1.3105,
|
| 726 |
+
"step": 1000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.02798745871361037,
|
| 730 |
+
"eval_complexity_accuracy": 0.0,
|
| 731 |
+
"eval_loss": 1.364721655845642,
|
| 732 |
+
"eval_runtime": 34.1546,
|
| 733 |
+
"eval_samples_per_second": 14.639,
|
| 734 |
+
"eval_steps_per_second": 1.845,
|
| 735 |
+
"step": 1002
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.02821091147779089,
|
| 739 |
+
"grad_norm": 12.720813751220703,
|
| 740 |
+
"learning_rate": 1.943634433830512e-06,
|
| 741 |
+
"loss": 1.2763,
|
| 742 |
+
"step": 1010
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.028490227433016543,
|
| 746 |
+
"grad_norm": 10.137106895446777,
|
| 747 |
+
"learning_rate": 1.943075805820904e-06,
|
| 748 |
+
"loss": 1.3177,
|
| 749 |
+
"step": 1020
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.028769543388242193,
|
| 753 |
+
"grad_norm": 11.257421493530273,
|
| 754 |
+
"learning_rate": 1.9425171778112953e-06,
|
| 755 |
+
"loss": 1.3078,
|
| 756 |
+
"step": 1030
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.029048859343467848,
|
| 760 |
+
"grad_norm": 11.93409538269043,
|
| 761 |
+
"learning_rate": 1.941958549801687e-06,
|
| 762 |
+
"loss": 1.3251,
|
| 763 |
+
"step": 1040
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.0293281752986935,
|
| 767 |
+
"grad_norm": 12.464277267456055,
|
| 768 |
+
"learning_rate": 1.9413999217920785e-06,
|
| 769 |
+
"loss": 1.3199,
|
| 770 |
+
"step": 1050
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.029607491253919153,
|
| 774 |
+
"grad_norm": 12.42292308807373,
|
| 775 |
+
"learning_rate": 1.9408412937824703e-06,
|
| 776 |
+
"loss": 1.2815,
|
| 777 |
+
"step": 1060
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.029886807209144804,
|
| 781 |
+
"grad_norm": 11.653295516967773,
|
| 782 |
+
"learning_rate": 1.9402826657728616e-06,
|
| 783 |
+
"loss": 1.2948,
|
| 784 |
+
"step": 1070
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.030166123164370458,
|
| 788 |
+
"grad_norm": 12.255006790161133,
|
| 789 |
+
"learning_rate": 1.9397240377632534e-06,
|
| 790 |
+
"loss": 1.3263,
|
| 791 |
+
"step": 1080
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.03044543911959611,
|
| 795 |
+
"grad_norm": 10.424007415771484,
|
| 796 |
+
"learning_rate": 1.939165409753645e-06,
|
| 797 |
+
"loss": 1.2892,
|
| 798 |
+
"step": 1090
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.030724755074821763,
|
| 802 |
+
"grad_norm": 10.664515495300293,
|
| 803 |
+
"learning_rate": 1.9386067817440366e-06,
|
| 804 |
+
"loss": 1.3407,
|
| 805 |
+
"step": 1100
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.031004071030047414,
|
| 809 |
+
"grad_norm": 12.733943939208984,
|
| 810 |
+
"learning_rate": 1.9380481537344284e-06,
|
| 811 |
+
"loss": 1.348,
|
| 812 |
+
"step": 1110
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.03128338698527307,
|
| 816 |
+
"grad_norm": 10.41376781463623,
|
| 817 |
+
"learning_rate": 1.9374895257248197e-06,
|
| 818 |
+
"loss": 1.3827,
|
| 819 |
+
"step": 1120
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.03156270294049872,
|
| 823 |
+
"grad_norm": 13.944782257080078,
|
| 824 |
+
"learning_rate": 1.9369308977152115e-06,
|
| 825 |
+
"loss": 1.3218,
|
| 826 |
+
"step": 1130
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.03184201889572437,
|
| 830 |
+
"grad_norm": 12.373078346252441,
|
| 831 |
+
"learning_rate": 1.936372269705603e-06,
|
| 832 |
+
"loss": 1.2725,
|
| 833 |
+
"step": 1140
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.03212133485095002,
|
| 837 |
+
"grad_norm": 11.583971977233887,
|
| 838 |
+
"learning_rate": 1.9358136416959947e-06,
|
| 839 |
+
"loss": 1.2983,
|
| 840 |
+
"step": 1150
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.03240065080617568,
|
| 844 |
+
"grad_norm": 12.660507202148438,
|
| 845 |
+
"learning_rate": 1.935255013686386e-06,
|
| 846 |
+
"loss": 1.278,
|
| 847 |
+
"step": 1160
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.03267996676140133,
|
| 851 |
+
"grad_norm": 10.222640991210938,
|
| 852 |
+
"learning_rate": 1.934696385676778e-06,
|
| 853 |
+
"loss": 1.2866,
|
| 854 |
+
"step": 1170
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.03295928271662698,
|
| 858 |
+
"grad_norm": 12.668971061706543,
|
| 859 |
+
"learning_rate": 1.934137757667169e-06,
|
| 860 |
+
"loss": 1.3605,
|
| 861 |
+
"step": 1180
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.03323859867185263,
|
| 865 |
+
"grad_norm": 10.59626579284668,
|
| 866 |
+
"learning_rate": 1.933579129657561e-06,
|
| 867 |
+
"loss": 1.321,
|
| 868 |
+
"step": 1190
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.03351791462707829,
|
| 872 |
+
"grad_norm": 11.953704833984375,
|
| 873 |
+
"learning_rate": 1.9330205016479528e-06,
|
| 874 |
+
"loss": 1.2852,
|
| 875 |
+
"step": 1200
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.03379723058230394,
|
| 879 |
+
"grad_norm": 11.2271146774292,
|
| 880 |
+
"learning_rate": 1.932461873638344e-06,
|
| 881 |
+
"loss": 1.3196,
|
| 882 |
+
"step": 1210
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.03407654653752959,
|
| 886 |
+
"grad_norm": 10.453490257263184,
|
| 887 |
+
"learning_rate": 1.9319032456287355e-06,
|
| 888 |
+
"loss": 1.397,
|
| 889 |
+
"step": 1220
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.03435586249275524,
|
| 893 |
+
"grad_norm": 13.665384292602539,
|
| 894 |
+
"learning_rate": 1.9313446176191273e-06,
|
| 895 |
+
"loss": 1.3058,
|
| 896 |
+
"step": 1230
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.0346351784479809,
|
| 900 |
+
"grad_norm": 10.085427284240723,
|
| 901 |
+
"learning_rate": 1.930785989609519e-06,
|
| 902 |
+
"loss": 1.3081,
|
| 903 |
+
"step": 1240
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.03491449440320655,
|
| 907 |
+
"grad_norm": 12.101105690002441,
|
| 908 |
+
"learning_rate": 1.9302273615999105e-06,
|
| 909 |
+
"loss": 1.345,
|
| 910 |
+
"step": 1250
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.0351938103584322,
|
| 914 |
+
"grad_norm": 10.636537551879883,
|
| 915 |
+
"learning_rate": 1.9296687335903022e-06,
|
| 916 |
+
"loss": 1.3293,
|
| 917 |
+
"step": 1260
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.03547312631365785,
|
| 921 |
+
"grad_norm": 12.76969051361084,
|
| 922 |
+
"learning_rate": 1.9291101055806936e-06,
|
| 923 |
+
"loss": 1.3403,
|
| 924 |
+
"step": 1270
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.0357524422688835,
|
| 928 |
+
"grad_norm": 11.625609397888184,
|
| 929 |
+
"learning_rate": 1.9285514775710854e-06,
|
| 930 |
+
"loss": 1.2967,
|
| 931 |
+
"step": 1280
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.03603175822410916,
|
| 935 |
+
"grad_norm": 12.158754348754883,
|
| 936 |
+
"learning_rate": 1.927992849561477e-06,
|
| 937 |
+
"loss": 1.3727,
|
| 938 |
+
"step": 1290
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.03631107417933481,
|
| 942 |
+
"grad_norm": 13.211498260498047,
|
| 943 |
+
"learning_rate": 1.9274342215518685e-06,
|
| 944 |
+
"loss": 1.2925,
|
| 945 |
+
"step": 1300
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.03659039013456046,
|
| 949 |
+
"grad_norm": 16.932209014892578,
|
| 950 |
+
"learning_rate": 1.92687559354226e-06,
|
| 951 |
+
"loss": 1.3434,
|
| 952 |
+
"step": 1310
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.03686970608978611,
|
| 956 |
+
"grad_norm": 10.869868278503418,
|
| 957 |
+
"learning_rate": 1.9263169655326517e-06,
|
| 958 |
+
"loss": 1.3001,
|
| 959 |
+
"step": 1320
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.03714902204501177,
|
| 963 |
+
"grad_norm": 11.199213027954102,
|
| 964 |
+
"learning_rate": 1.9257583375230435e-06,
|
| 965 |
+
"loss": 1.3927,
|
| 966 |
+
"step": 1330
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.03742833800023742,
|
| 970 |
+
"grad_norm": 11.47125244140625,
|
| 971 |
+
"learning_rate": 1.925199709513435e-06,
|
| 972 |
+
"loss": 1.3426,
|
| 973 |
+
"step": 1340
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.03770765395546307,
|
| 977 |
+
"grad_norm": 12.344675064086914,
|
| 978 |
+
"learning_rate": 1.9246410815038266e-06,
|
| 979 |
+
"loss": 1.3525,
|
| 980 |
+
"step": 1350
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.03798696991068872,
|
| 984 |
+
"grad_norm": 12.831677436828613,
|
| 985 |
+
"learning_rate": 1.924082453494218e-06,
|
| 986 |
+
"loss": 1.329,
|
| 987 |
+
"step": 1360
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.03826628586591438,
|
| 991 |
+
"grad_norm": 11.5836763381958,
|
| 992 |
+
"learning_rate": 1.92352382548461e-06,
|
| 993 |
+
"loss": 1.3188,
|
| 994 |
+
"step": 1370
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.03854560182114003,
|
| 998 |
+
"grad_norm": 10.466170310974121,
|
| 999 |
+
"learning_rate": 1.9229651974750016e-06,
|
| 1000 |
+
"loss": 1.3177,
|
| 1001 |
+
"step": 1380
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.03882491777636568,
|
| 1005 |
+
"grad_norm": 12.394039154052734,
|
| 1006 |
+
"learning_rate": 1.922406569465393e-06,
|
| 1007 |
+
"loss": 1.3367,
|
| 1008 |
+
"step": 1390
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.03910423373159133,
|
| 1012 |
+
"grad_norm": 10.985048294067383,
|
| 1013 |
+
"learning_rate": 1.9218479414557843e-06,
|
| 1014 |
+
"loss": 1.2887,
|
| 1015 |
+
"step": 1400
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.03938354968681698,
|
| 1019 |
+
"grad_norm": 12.47451400756836,
|
| 1020 |
+
"learning_rate": 1.921289313446176e-06,
|
| 1021 |
+
"loss": 1.2986,
|
| 1022 |
+
"step": 1410
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.03966286564204264,
|
| 1026 |
+
"grad_norm": 10.245006561279297,
|
| 1027 |
+
"learning_rate": 1.920730685436568e-06,
|
| 1028 |
+
"loss": 1.3413,
|
| 1029 |
+
"step": 1420
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.03994218159726829,
|
| 1033 |
+
"grad_norm": 11.382227897644043,
|
| 1034 |
+
"learning_rate": 1.9201720574269593e-06,
|
| 1035 |
+
"loss": 1.3652,
|
| 1036 |
+
"step": 1430
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.04022149755249394,
|
| 1040 |
+
"grad_norm": 13.765195846557617,
|
| 1041 |
+
"learning_rate": 1.919613429417351e-06,
|
| 1042 |
+
"loss": 1.3105,
|
| 1043 |
+
"step": 1440
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.04050081350771959,
|
| 1047 |
+
"grad_norm": 10.82947063446045,
|
| 1048 |
+
"learning_rate": 1.9190548014077424e-06,
|
| 1049 |
+
"loss": 1.3128,
|
| 1050 |
+
"step": 1450
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.04078012946294525,
|
| 1054 |
+
"grad_norm": 9.862834930419922,
|
| 1055 |
+
"learning_rate": 1.918496173398134e-06,
|
| 1056 |
+
"loss": 1.3368,
|
| 1057 |
+
"step": 1460
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.0410594454181709,
|
| 1061 |
+
"grad_norm": 9.987138748168945,
|
| 1062 |
+
"learning_rate": 1.9179375453885256e-06,
|
| 1063 |
+
"loss": 1.3172,
|
| 1064 |
+
"step": 1470
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.04133876137339655,
|
| 1068 |
+
"grad_norm": 10.993836402893066,
|
| 1069 |
+
"learning_rate": 1.9173789173789174e-06,
|
| 1070 |
+
"loss": 1.2961,
|
| 1071 |
+
"step": 1480
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.0416180773286222,
|
| 1075 |
+
"grad_norm": 10.989373207092285,
|
| 1076 |
+
"learning_rate": 1.9168202893693087e-06,
|
| 1077 |
+
"loss": 1.2854,
|
| 1078 |
+
"step": 1490
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.04189739328384786,
|
| 1082 |
+
"grad_norm": 14.129310607910156,
|
| 1083 |
+
"learning_rate": 1.9162616613597005e-06,
|
| 1084 |
+
"loss": 1.3157,
|
| 1085 |
+
"step": 1500
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.04198118807041555,
|
| 1089 |
+
"eval_complexity_accuracy": 0.0,
|
| 1090 |
+
"eval_loss": 1.3546726703643799,
|
| 1091 |
+
"eval_runtime": 34.0455,
|
| 1092 |
+
"eval_samples_per_second": 14.686,
|
| 1093 |
+
"eval_steps_per_second": 1.85,
|
| 1094 |
+
"step": 1503
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.04217670923907351,
|
| 1098 |
+
"grad_norm": 10.534819602966309,
|
| 1099 |
+
"learning_rate": 1.9157030333500923e-06,
|
| 1100 |
+
"loss": 1.3115,
|
| 1101 |
+
"step": 1510
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.04245602519429916,
|
| 1105 |
+
"grad_norm": 10.998124122619629,
|
| 1106 |
+
"learning_rate": 1.9151444053404837e-06,
|
| 1107 |
+
"loss": 1.2958,
|
| 1108 |
+
"step": 1520
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.04273534114952481,
|
| 1112 |
+
"grad_norm": 10.543405532836914,
|
| 1113 |
+
"learning_rate": 1.9145857773308754e-06,
|
| 1114 |
+
"loss": 1.2976,
|
| 1115 |
+
"step": 1530
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.04301465710475046,
|
| 1119 |
+
"grad_norm": 11.423952102661133,
|
| 1120 |
+
"learning_rate": 1.914027149321267e-06,
|
| 1121 |
+
"loss": 1.2922,
|
| 1122 |
+
"step": 1540
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.04329397305997612,
|
| 1126 |
+
"grad_norm": 10.33931827545166,
|
| 1127 |
+
"learning_rate": 1.9134685213116586e-06,
|
| 1128 |
+
"loss": 1.3221,
|
| 1129 |
+
"step": 1550
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.04357328901520177,
|
| 1133 |
+
"grad_norm": 10.731399536132812,
|
| 1134 |
+
"learning_rate": 1.91290989330205e-06,
|
| 1135 |
+
"loss": 1.2949,
|
| 1136 |
+
"step": 1560
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.04385260497042742,
|
| 1140 |
+
"grad_norm": 10.743152618408203,
|
| 1141 |
+
"learning_rate": 1.9123512652924418e-06,
|
| 1142 |
+
"loss": 1.275,
|
| 1143 |
+
"step": 1570
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.04413192092565307,
|
| 1147 |
+
"grad_norm": 10.677448272705078,
|
| 1148 |
+
"learning_rate": 1.911792637282833e-06,
|
| 1149 |
+
"loss": 1.2822,
|
| 1150 |
+
"step": 1580
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.04441123688087873,
|
| 1154 |
+
"grad_norm": 10.933751106262207,
|
| 1155 |
+
"learning_rate": 1.911234009273225e-06,
|
| 1156 |
+
"loss": 1.2784,
|
| 1157 |
+
"step": 1590
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.04469055283610438,
|
| 1161 |
+
"grad_norm": 10.95008659362793,
|
| 1162 |
+
"learning_rate": 1.9106753812636167e-06,
|
| 1163 |
+
"loss": 1.337,
|
| 1164 |
+
"step": 1600
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.04496986879133003,
|
| 1168 |
+
"grad_norm": 11.022769927978516,
|
| 1169 |
+
"learning_rate": 1.910116753254008e-06,
|
| 1170 |
+
"loss": 1.3194,
|
| 1171 |
+
"step": 1610
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.04524918474655568,
|
| 1175 |
+
"grad_norm": 12.916274070739746,
|
| 1176 |
+
"learning_rate": 1.9095581252444e-06,
|
| 1177 |
+
"loss": 1.3023,
|
| 1178 |
+
"step": 1620
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.04552850070178134,
|
| 1182 |
+
"grad_norm": 12.046470642089844,
|
| 1183 |
+
"learning_rate": 1.9089994972347912e-06,
|
| 1184 |
+
"loss": 1.2803,
|
| 1185 |
+
"step": 1630
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.04580781665700699,
|
| 1189 |
+
"grad_norm": 10.913056373596191,
|
| 1190 |
+
"learning_rate": 1.9084408692251826e-06,
|
| 1191 |
+
"loss": 1.3405,
|
| 1192 |
+
"step": 1640
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.04608713261223264,
|
| 1196 |
+
"grad_norm": 11.769244194030762,
|
| 1197 |
+
"learning_rate": 1.9078822412155744e-06,
|
| 1198 |
+
"loss": 1.2995,
|
| 1199 |
+
"step": 1650
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.04636644856745829,
|
| 1203 |
+
"grad_norm": 11.765388488769531,
|
| 1204 |
+
"learning_rate": 1.907323613205966e-06,
|
| 1205 |
+
"loss": 1.3457,
|
| 1206 |
+
"step": 1660
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.046645764522683944,
|
| 1210 |
+
"grad_norm": 11.881918907165527,
|
| 1211 |
+
"learning_rate": 1.9067649851963577e-06,
|
| 1212 |
+
"loss": 1.3367,
|
| 1213 |
+
"step": 1670
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.0469250804779096,
|
| 1217 |
+
"grad_norm": 10.628633499145508,
|
| 1218 |
+
"learning_rate": 1.9062063571867493e-06,
|
| 1219 |
+
"loss": 1.3091,
|
| 1220 |
+
"step": 1680
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.04720439643313525,
|
| 1224 |
+
"grad_norm": 11.146201133728027,
|
| 1225 |
+
"learning_rate": 1.9056477291771409e-06,
|
| 1226 |
+
"loss": 1.3041,
|
| 1227 |
+
"step": 1690
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.0474837123883609,
|
| 1231 |
+
"grad_norm": 10.595499992370605,
|
| 1232 |
+
"learning_rate": 1.9050891011675325e-06,
|
| 1233 |
+
"loss": 1.3185,
|
| 1234 |
+
"step": 1700
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.047763028343586554,
|
| 1238 |
+
"grad_norm": 12.041298866271973,
|
| 1239 |
+
"learning_rate": 1.904530473157924e-06,
|
| 1240 |
+
"loss": 1.3244,
|
| 1241 |
+
"step": 1710
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.04804234429881221,
|
| 1245 |
+
"grad_norm": 11.456694602966309,
|
| 1246 |
+
"learning_rate": 1.9039718451483156e-06,
|
| 1247 |
+
"loss": 1.2795,
|
| 1248 |
+
"step": 1720
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.04832166025403786,
|
| 1252 |
+
"grad_norm": 10.448249816894531,
|
| 1253 |
+
"learning_rate": 1.9034132171387072e-06,
|
| 1254 |
+
"loss": 1.2914,
|
| 1255 |
+
"step": 1730
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.04860097620926351,
|
| 1259 |
+
"grad_norm": 11.16418170928955,
|
| 1260 |
+
"learning_rate": 1.9028545891290988e-06,
|
| 1261 |
+
"loss": 1.3405,
|
| 1262 |
+
"step": 1740
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.048880292164489164,
|
| 1266 |
+
"grad_norm": 11.179234504699707,
|
| 1267 |
+
"learning_rate": 1.9022959611194903e-06,
|
| 1268 |
+
"loss": 1.3432,
|
| 1269 |
+
"step": 1750
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.04915960811971482,
|
| 1273 |
+
"grad_norm": 10.457565307617188,
|
| 1274 |
+
"learning_rate": 1.9017373331098821e-06,
|
| 1275 |
+
"loss": 1.3358,
|
| 1276 |
+
"step": 1760
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.04943892407494047,
|
| 1280 |
+
"grad_norm": 11.272239685058594,
|
| 1281 |
+
"learning_rate": 1.9011787051002737e-06,
|
| 1282 |
+
"loss": 1.2664,
|
| 1283 |
+
"step": 1770
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.04971824003016612,
|
| 1287 |
+
"grad_norm": 11.015891075134277,
|
| 1288 |
+
"learning_rate": 1.9006200770906653e-06,
|
| 1289 |
+
"loss": 1.2642,
|
| 1290 |
+
"step": 1780
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.049997555985391774,
|
| 1294 |
+
"grad_norm": 10.243793487548828,
|
| 1295 |
+
"learning_rate": 1.9000614490810569e-06,
|
| 1296 |
+
"loss": 1.2335,
|
| 1297 |
+
"step": 1790
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.050276871940617425,
|
| 1301 |
+
"grad_norm": 11.970431327819824,
|
| 1302 |
+
"learning_rate": 1.8995028210714484e-06,
|
| 1303 |
+
"loss": 1.2568,
|
| 1304 |
+
"step": 1800
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.05055618789584308,
|
| 1308 |
+
"grad_norm": 9.61301040649414,
|
| 1309 |
+
"learning_rate": 1.89894419306184e-06,
|
| 1310 |
+
"loss": 1.2969,
|
| 1311 |
+
"step": 1810
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.050835503851068733,
|
| 1315 |
+
"grad_norm": 10.591397285461426,
|
| 1316 |
+
"learning_rate": 1.8983855650522316e-06,
|
| 1317 |
+
"loss": 1.3004,
|
| 1318 |
+
"step": 1820
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.051114819806294384,
|
| 1322 |
+
"grad_norm": 15.13564682006836,
|
| 1323 |
+
"learning_rate": 1.8978269370426232e-06,
|
| 1324 |
+
"loss": 1.2676,
|
| 1325 |
+
"step": 1830
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.051394135761520035,
|
| 1329 |
+
"grad_norm": 10.456026077270508,
|
| 1330 |
+
"learning_rate": 1.8972683090330148e-06,
|
| 1331 |
+
"loss": 1.254,
|
| 1332 |
+
"step": 1840
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.05167345171674569,
|
| 1336 |
+
"grad_norm": 11.265973091125488,
|
| 1337 |
+
"learning_rate": 1.8967096810234065e-06,
|
| 1338 |
+
"loss": 1.2651,
|
| 1339 |
+
"step": 1850
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.051952767671971344,
|
| 1343 |
+
"grad_norm": 10.13062858581543,
|
| 1344 |
+
"learning_rate": 1.8961510530137981e-06,
|
| 1345 |
+
"loss": 1.3549,
|
| 1346 |
+
"step": 1860
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.052232083627196994,
|
| 1350 |
+
"grad_norm": 10.586962699890137,
|
| 1351 |
+
"learning_rate": 1.8955924250041897e-06,
|
| 1352 |
+
"loss": 1.326,
|
| 1353 |
+
"step": 1870
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.052511399582422645,
|
| 1357 |
+
"grad_norm": 11.121024131774902,
|
| 1358 |
+
"learning_rate": 1.8950337969945813e-06,
|
| 1359 |
+
"loss": 1.2838,
|
| 1360 |
+
"step": 1880
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.052790715537648296,
|
| 1364 |
+
"grad_norm": 10.71886920928955,
|
| 1365 |
+
"learning_rate": 1.8944751689849726e-06,
|
| 1366 |
+
"loss": 1.2793,
|
| 1367 |
+
"step": 1890
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.053070031492873954,
|
| 1371 |
+
"grad_norm": 10.959943771362305,
|
| 1372 |
+
"learning_rate": 1.8939165409753644e-06,
|
| 1373 |
+
"loss": 1.2731,
|
| 1374 |
+
"step": 1900
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.053349347448099604,
|
| 1378 |
+
"grad_norm": 11.72314453125,
|
| 1379 |
+
"learning_rate": 1.893357912965756e-06,
|
| 1380 |
+
"loss": 1.3049,
|
| 1381 |
+
"step": 1910
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.053628663403325255,
|
| 1385 |
+
"grad_norm": 11.75049114227295,
|
| 1386 |
+
"learning_rate": 1.8927992849561476e-06,
|
| 1387 |
+
"loss": 1.273,
|
| 1388 |
+
"step": 1920
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.053907979358550906,
|
| 1392 |
+
"grad_norm": 11.237908363342285,
|
| 1393 |
+
"learning_rate": 1.8922406569465392e-06,
|
| 1394 |
+
"loss": 1.3405,
|
| 1395 |
+
"step": 1930
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.054187295313776564,
|
| 1399 |
+
"grad_norm": 13.297497749328613,
|
| 1400 |
+
"learning_rate": 1.891682028936931e-06,
|
| 1401 |
+
"loss": 1.3276,
|
| 1402 |
+
"step": 1940
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.054466611269002214,
|
| 1406 |
+
"grad_norm": 12.209798812866211,
|
| 1407 |
+
"learning_rate": 1.8911234009273225e-06,
|
| 1408 |
+
"loss": 1.3376,
|
| 1409 |
+
"step": 1950
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.054745927224227865,
|
| 1413 |
+
"grad_norm": 13.262669563293457,
|
| 1414 |
+
"learning_rate": 1.890564772917714e-06,
|
| 1415 |
+
"loss": 1.2976,
|
| 1416 |
+
"step": 1960
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.055025243179453516,
|
| 1420 |
+
"grad_norm": 10.766546249389648,
|
| 1421 |
+
"learning_rate": 1.8900061449081055e-06,
|
| 1422 |
+
"loss": 1.3522,
|
| 1423 |
+
"step": 1970
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.055304559134679174,
|
| 1427 |
+
"grad_norm": 10.29268741607666,
|
| 1428 |
+
"learning_rate": 1.889447516898497e-06,
|
| 1429 |
+
"loss": 1.28,
|
| 1430 |
+
"step": 1980
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.055583875089904825,
|
| 1434 |
+
"grad_norm": 11.653640747070312,
|
| 1435 |
+
"learning_rate": 1.8888888888888888e-06,
|
| 1436 |
+
"loss": 1.2993,
|
| 1437 |
+
"step": 1990
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.055863191045130475,
|
| 1441 |
+
"grad_norm": 10.069348335266113,
|
| 1442 |
+
"learning_rate": 1.8883302608792804e-06,
|
| 1443 |
+
"loss": 1.27,
|
| 1444 |
+
"step": 2000
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.05597491742722074,
|
| 1448 |
+
"eval_complexity_accuracy": 0.0,
|
| 1449 |
+
"eval_loss": 1.3485850095748901,
|
| 1450 |
+
"eval_runtime": 34.0417,
|
| 1451 |
+
"eval_samples_per_second": 14.688,
|
| 1452 |
+
"eval_steps_per_second": 1.851,
|
| 1453 |
+
"step": 2004
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.056142507000356126,
|
| 1457 |
+
"grad_norm": 10.894604682922363,
|
| 1458 |
+
"learning_rate": 1.887771632869672e-06,
|
| 1459 |
+
"loss": 1.3105,
|
| 1460 |
+
"step": 2010
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.05642182295558178,
|
| 1464 |
+
"grad_norm": 11.579715728759766,
|
| 1465 |
+
"learning_rate": 1.8872130048600636e-06,
|
| 1466 |
+
"loss": 1.2776,
|
| 1467 |
+
"step": 2020
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.056701138910807435,
|
| 1471 |
+
"grad_norm": 10.074790000915527,
|
| 1472 |
+
"learning_rate": 1.8866543768504553e-06,
|
| 1473 |
+
"loss": 1.3366,
|
| 1474 |
+
"step": 2030
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.056980454866033085,
|
| 1478 |
+
"grad_norm": 11.219857215881348,
|
| 1479 |
+
"learning_rate": 1.886095748840847e-06,
|
| 1480 |
+
"loss": 1.2873,
|
| 1481 |
+
"step": 2040
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.057259770821258736,
|
| 1485 |
+
"grad_norm": 10.627588272094727,
|
| 1486 |
+
"learning_rate": 1.8855371208312385e-06,
|
| 1487 |
+
"loss": 1.3311,
|
| 1488 |
+
"step": 2050
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 0.05753908677648439,
|
| 1492 |
+
"grad_norm": 10.92846393585205,
|
| 1493 |
+
"learning_rate": 1.8849784928216299e-06,
|
| 1494 |
+
"loss": 1.3101,
|
| 1495 |
+
"step": 2060
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.057818402731710045,
|
| 1499 |
+
"grad_norm": 11.262550354003906,
|
| 1500 |
+
"learning_rate": 1.8844198648120214e-06,
|
| 1501 |
+
"loss": 1.3465,
|
| 1502 |
+
"step": 2070
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 0.058097718686935695,
|
| 1506 |
+
"grad_norm": 13.099771499633789,
|
| 1507 |
+
"learning_rate": 1.8838612368024132e-06,
|
| 1508 |
+
"loss": 1.3157,
|
| 1509 |
+
"step": 2080
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.058377034642161346,
|
| 1513 |
+
"grad_norm": 9.9907865524292,
|
| 1514 |
+
"learning_rate": 1.8833026087928048e-06,
|
| 1515 |
+
"loss": 1.298,
|
| 1516 |
+
"step": 2090
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.058656350597387,
|
| 1520 |
+
"grad_norm": 10.225235939025879,
|
| 1521 |
+
"learning_rate": 1.8827439807831964e-06,
|
| 1522 |
+
"loss": 1.2737,
|
| 1523 |
+
"step": 2100
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 0.058935666552612655,
|
| 1527 |
+
"grad_norm": 14.671952247619629,
|
| 1528 |
+
"learning_rate": 1.882185352773588e-06,
|
| 1529 |
+
"loss": 1.2994,
|
| 1530 |
+
"step": 2110
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.059214982507838305,
|
| 1534 |
+
"grad_norm": 10.452831268310547,
|
| 1535 |
+
"learning_rate": 1.8816267247639797e-06,
|
| 1536 |
+
"loss": 1.3168,
|
| 1537 |
+
"step": 2120
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 0.059494298463063956,
|
| 1541 |
+
"grad_norm": 11.753946304321289,
|
| 1542 |
+
"learning_rate": 1.8810680967543713e-06,
|
| 1543 |
+
"loss": 1.3209,
|
| 1544 |
+
"step": 2130
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 0.05977361441828961,
|
| 1548 |
+
"grad_norm": 11.631643295288086,
|
| 1549 |
+
"learning_rate": 1.8805094687447627e-06,
|
| 1550 |
+
"loss": 1.3339,
|
| 1551 |
+
"step": 2140
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.06005293037351526,
|
| 1555 |
+
"grad_norm": 11.326909065246582,
|
| 1556 |
+
"learning_rate": 1.8799508407351543e-06,
|
| 1557 |
+
"loss": 1.3191,
|
| 1558 |
+
"step": 2150
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 0.060332246328740916,
|
| 1562 |
+
"grad_norm": 11.047061920166016,
|
| 1563 |
+
"learning_rate": 1.8793922127255458e-06,
|
| 1564 |
+
"loss": 1.346,
|
| 1565 |
+
"step": 2160
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 0.060611562283966566,
|
| 1569 |
+
"grad_norm": 11.53350830078125,
|
| 1570 |
+
"learning_rate": 1.8788335847159376e-06,
|
| 1571 |
+
"loss": 1.3125,
|
| 1572 |
+
"step": 2170
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 0.06089087823919222,
|
| 1576 |
+
"grad_norm": 11.501274108886719,
|
| 1577 |
+
"learning_rate": 1.8782749567063292e-06,
|
| 1578 |
+
"loss": 1.3432,
|
| 1579 |
+
"step": 2180
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.06117019419441787,
|
| 1583 |
+
"grad_norm": 11.525626182556152,
|
| 1584 |
+
"learning_rate": 1.8777163286967208e-06,
|
| 1585 |
+
"loss": 1.362,
|
| 1586 |
+
"step": 2190
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.061449510149643526,
|
| 1590 |
+
"grad_norm": 13.74886703491211,
|
| 1591 |
+
"learning_rate": 1.8771577006871124e-06,
|
| 1592 |
+
"loss": 1.3157,
|
| 1593 |
+
"step": 2200
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.061728826104869176,
|
| 1597 |
+
"grad_norm": 12.192688941955566,
|
| 1598 |
+
"learning_rate": 1.8765990726775042e-06,
|
| 1599 |
+
"loss": 1.287,
|
| 1600 |
+
"step": 2210
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.06200814206009483,
|
| 1604 |
+
"grad_norm": 10.64345645904541,
|
| 1605 |
+
"learning_rate": 1.8760404446678955e-06,
|
| 1606 |
+
"loss": 1.2499,
|
| 1607 |
+
"step": 2220
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.06228745801532048,
|
| 1611 |
+
"grad_norm": 11.966428756713867,
|
| 1612 |
+
"learning_rate": 1.875481816658287e-06,
|
| 1613 |
+
"loss": 1.2789,
|
| 1614 |
+
"step": 2230
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.06256677397054614,
|
| 1618 |
+
"grad_norm": 11.889241218566895,
|
| 1619 |
+
"learning_rate": 1.8749231886486787e-06,
|
| 1620 |
+
"loss": 1.2621,
|
| 1621 |
+
"step": 2240
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.06284608992577179,
|
| 1625 |
+
"grad_norm": 13.372054100036621,
|
| 1626 |
+
"learning_rate": 1.8743645606390702e-06,
|
| 1627 |
+
"loss": 1.3493,
|
| 1628 |
+
"step": 2250
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.06312540588099744,
|
| 1632 |
+
"grad_norm": 10.879005432128906,
|
| 1633 |
+
"learning_rate": 1.873805932629462e-06,
|
| 1634 |
+
"loss": 1.3077,
|
| 1635 |
+
"step": 2260
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.06340472183622309,
|
| 1639 |
+
"grad_norm": 11.956343650817871,
|
| 1640 |
+
"learning_rate": 1.8732473046198536e-06,
|
| 1641 |
+
"loss": 1.3108,
|
| 1642 |
+
"step": 2270
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 0.06368403779144874,
|
| 1646 |
+
"grad_norm": 11.269684791564941,
|
| 1647 |
+
"learning_rate": 1.8726886766102452e-06,
|
| 1648 |
+
"loss": 1.2956,
|
| 1649 |
+
"step": 2280
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 0.06396335374667439,
|
| 1653 |
+
"grad_norm": 13.093775749206543,
|
| 1654 |
+
"learning_rate": 1.8721300486006368e-06,
|
| 1655 |
+
"loss": 1.2553,
|
| 1656 |
+
"step": 2290
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 0.06424266970190004,
|
| 1660 |
+
"grad_norm": 9.943842887878418,
|
| 1661 |
+
"learning_rate": 1.8715714205910286e-06,
|
| 1662 |
+
"loss": 1.2936,
|
| 1663 |
+
"step": 2300
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.0645219856571257,
|
| 1667 |
+
"grad_norm": 10.660123825073242,
|
| 1668 |
+
"learning_rate": 1.87101279258142e-06,
|
| 1669 |
+
"loss": 1.3319,
|
| 1670 |
+
"step": 2310
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 0.06480130161235136,
|
| 1674 |
+
"grad_norm": 11.023526191711426,
|
| 1675 |
+
"learning_rate": 1.8704541645718115e-06,
|
| 1676 |
+
"loss": 1.3441,
|
| 1677 |
+
"step": 2320
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.065080617567577,
|
| 1681 |
+
"grad_norm": 11.04121208190918,
|
| 1682 |
+
"learning_rate": 1.869895536562203e-06,
|
| 1683 |
+
"loss": 1.3157,
|
| 1684 |
+
"step": 2330
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 0.06535993352280266,
|
| 1688 |
+
"grad_norm": 10.915820121765137,
|
| 1689 |
+
"learning_rate": 1.8693369085525946e-06,
|
| 1690 |
+
"loss": 1.2891,
|
| 1691 |
+
"step": 2340
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 0.06563924947802831,
|
| 1695 |
+
"grad_norm": 11.1669282913208,
|
| 1696 |
+
"learning_rate": 1.8687782805429864e-06,
|
| 1697 |
+
"loss": 1.3301,
|
| 1698 |
+
"step": 2350
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 0.06591856543325396,
|
| 1702 |
+
"grad_norm": 13.473467826843262,
|
| 1703 |
+
"learning_rate": 1.868219652533378e-06,
|
| 1704 |
+
"loss": 1.3412,
|
| 1705 |
+
"step": 2360
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.06619788138847961,
|
| 1709 |
+
"grad_norm": 9.66751480102539,
|
| 1710 |
+
"learning_rate": 1.8676610245237696e-06,
|
| 1711 |
+
"loss": 1.4053,
|
| 1712 |
+
"step": 2370
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.06647719734370526,
|
| 1716 |
+
"grad_norm": 10.621736526489258,
|
| 1717 |
+
"learning_rate": 1.8671023965141612e-06,
|
| 1718 |
+
"loss": 1.301,
|
| 1719 |
+
"step": 2380
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.06675651329893093,
|
| 1723 |
+
"grad_norm": 12.115357398986816,
|
| 1724 |
+
"learning_rate": 1.8665437685045527e-06,
|
| 1725 |
+
"loss": 1.3193,
|
| 1726 |
+
"step": 2390
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.06703582925415658,
|
| 1730 |
+
"grad_norm": 10.837126731872559,
|
| 1731 |
+
"learning_rate": 1.8659851404949443e-06,
|
| 1732 |
+
"loss": 1.2737,
|
| 1733 |
+
"step": 2400
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.06731514520938223,
|
| 1737 |
+
"grad_norm": 11.175081253051758,
|
| 1738 |
+
"learning_rate": 1.865426512485336e-06,
|
| 1739 |
+
"loss": 1.3254,
|
| 1740 |
+
"step": 2410
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.06759446116460788,
|
| 1744 |
+
"grad_norm": 11.028107643127441,
|
| 1745 |
+
"learning_rate": 1.8648678844757275e-06,
|
| 1746 |
+
"loss": 1.3037,
|
| 1747 |
+
"step": 2420
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.06787377711983353,
|
| 1751 |
+
"grad_norm": 11.444878578186035,
|
| 1752 |
+
"learning_rate": 1.864309256466119e-06,
|
| 1753 |
+
"loss": 1.3237,
|
| 1754 |
+
"step": 2430
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.06815309307505918,
|
| 1758 |
+
"grad_norm": 10.279289245605469,
|
| 1759 |
+
"learning_rate": 1.8637506284565108e-06,
|
| 1760 |
+
"loss": 1.2836,
|
| 1761 |
+
"step": 2440
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.06843240903028483,
|
| 1765 |
+
"grad_norm": 10.37401008605957,
|
| 1766 |
+
"learning_rate": 1.8631920004469024e-06,
|
| 1767 |
+
"loss": 1.3329,
|
| 1768 |
+
"step": 2450
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.06871172498551048,
|
| 1772 |
+
"grad_norm": 9.833236694335938,
|
| 1773 |
+
"learning_rate": 1.862633372437294e-06,
|
| 1774 |
+
"loss": 1.3125,
|
| 1775 |
+
"step": 2460
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.06899104094073613,
|
| 1779 |
+
"grad_norm": 11.059619903564453,
|
| 1780 |
+
"learning_rate": 1.8620747444276854e-06,
|
| 1781 |
+
"loss": 1.2746,
|
| 1782 |
+
"step": 2470
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.0692703568959618,
|
| 1786 |
+
"grad_norm": 10.897518157958984,
|
| 1787 |
+
"learning_rate": 1.8615161164180771e-06,
|
| 1788 |
+
"loss": 1.2552,
|
| 1789 |
+
"step": 2480
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.06954967285118745,
|
| 1793 |
+
"grad_norm": 12.665666580200195,
|
| 1794 |
+
"learning_rate": 1.8609574884084687e-06,
|
| 1795 |
+
"loss": 1.3093,
|
| 1796 |
+
"step": 2490
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.0698289888064131,
|
| 1800 |
+
"grad_norm": 10.878984451293945,
|
| 1801 |
+
"learning_rate": 1.8603988603988603e-06,
|
| 1802 |
+
"loss": 1.291,
|
| 1803 |
+
"step": 2500
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.06996864678402592,
|
| 1807 |
+
"eval_complexity_accuracy": 0.0,
|
| 1808 |
+
"eval_loss": 1.3446284532546997,
|
| 1809 |
+
"eval_runtime": 33.87,
|
| 1810 |
+
"eval_samples_per_second": 14.762,
|
| 1811 |
+
"eval_steps_per_second": 1.86,
|
| 1812 |
+
"step": 2505
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 0.07010830476163875,
|
| 1816 |
+
"grad_norm": 11.848414421081543,
|
| 1817 |
+
"learning_rate": 1.8598402323892519e-06,
|
| 1818 |
+
"loss": 1.3266,
|
| 1819 |
+
"step": 2510
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.0703876207168644,
|
| 1823 |
+
"grad_norm": 11.258633613586426,
|
| 1824 |
+
"learning_rate": 1.8592816043796435e-06,
|
| 1825 |
+
"loss": 1.2747,
|
| 1826 |
+
"step": 2520
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.07066693667209005,
|
| 1830 |
+
"grad_norm": 12.249394416809082,
|
| 1831 |
+
"learning_rate": 1.8587229763700352e-06,
|
| 1832 |
+
"loss": 1.2717,
|
| 1833 |
+
"step": 2530
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.0709462526273157,
|
| 1837 |
+
"grad_norm": 11.384076118469238,
|
| 1838 |
+
"learning_rate": 1.8581643483604268e-06,
|
| 1839 |
+
"loss": 1.3339,
|
| 1840 |
+
"step": 2540
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 0.07122556858254135,
|
| 1844 |
+
"grad_norm": 11.27473258972168,
|
| 1845 |
+
"learning_rate": 1.8576057203508182e-06,
|
| 1846 |
+
"loss": 1.2737,
|
| 1847 |
+
"step": 2550
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 0.071504884537767,
|
| 1851 |
+
"grad_norm": 11.083890914916992,
|
| 1852 |
+
"learning_rate": 1.8570470923412098e-06,
|
| 1853 |
+
"loss": 1.3492,
|
| 1854 |
+
"step": 2560
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 0.07178420049299267,
|
| 1858 |
+
"grad_norm": 12.925027847290039,
|
| 1859 |
+
"learning_rate": 1.8564884643316015e-06,
|
| 1860 |
+
"loss": 1.3546,
|
| 1861 |
+
"step": 2570
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.07206351644821832,
|
| 1865 |
+
"grad_norm": 11.500834465026855,
|
| 1866 |
+
"learning_rate": 1.8559298363219931e-06,
|
| 1867 |
+
"loss": 1.2662,
|
| 1868 |
+
"step": 2580
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.07234283240344397,
|
| 1872 |
+
"grad_norm": 10.518533706665039,
|
| 1873 |
+
"learning_rate": 1.8553712083123847e-06,
|
| 1874 |
+
"loss": 1.2815,
|
| 1875 |
+
"step": 2590
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.07262214835866962,
|
| 1879 |
+
"grad_norm": 12.124496459960938,
|
| 1880 |
+
"learning_rate": 1.8548125803027763e-06,
|
| 1881 |
+
"loss": 1.312,
|
| 1882 |
+
"step": 2600
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.07290146431389527,
|
| 1886 |
+
"grad_norm": 10.693092346191406,
|
| 1887 |
+
"learning_rate": 1.8542539522931679e-06,
|
| 1888 |
+
"loss": 1.3071,
|
| 1889 |
+
"step": 2610
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.07318078026912092,
|
| 1893 |
+
"grad_norm": 9.837552070617676,
|
| 1894 |
+
"learning_rate": 1.8536953242835596e-06,
|
| 1895 |
+
"loss": 1.2985,
|
| 1896 |
+
"step": 2620
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.07346009622434657,
|
| 1900 |
+
"grad_norm": 11.058207511901855,
|
| 1901 |
+
"learning_rate": 1.8531366962739512e-06,
|
| 1902 |
+
"loss": 1.3406,
|
| 1903 |
+
"step": 2630
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.07373941217957222,
|
| 1907 |
+
"grad_norm": 10.664831161499023,
|
| 1908 |
+
"learning_rate": 1.8525780682643426e-06,
|
| 1909 |
+
"loss": 1.3086,
|
| 1910 |
+
"step": 2640
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.07401872813479787,
|
| 1914 |
+
"grad_norm": 11.020722389221191,
|
| 1915 |
+
"learning_rate": 1.8520194402547342e-06,
|
| 1916 |
+
"loss": 1.2951,
|
| 1917 |
+
"step": 2650
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.07429804409002354,
|
| 1921 |
+
"grad_norm": 11.75809383392334,
|
| 1922 |
+
"learning_rate": 1.851460812245126e-06,
|
| 1923 |
+
"loss": 1.2933,
|
| 1924 |
+
"step": 2660
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 0.07457736004524919,
|
| 1928 |
+
"grad_norm": 11.260404586791992,
|
| 1929 |
+
"learning_rate": 1.8509021842355175e-06,
|
| 1930 |
+
"loss": 1.3669,
|
| 1931 |
+
"step": 2670
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 0.07485667600047484,
|
| 1935 |
+
"grad_norm": 11.38213062286377,
|
| 1936 |
+
"learning_rate": 1.8503435562259091e-06,
|
| 1937 |
+
"loss": 1.3048,
|
| 1938 |
+
"step": 2680
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.07513599195570049,
|
| 1942 |
+
"grad_norm": 10.554960250854492,
|
| 1943 |
+
"learning_rate": 1.8497849282163007e-06,
|
| 1944 |
+
"loss": 1.3218,
|
| 1945 |
+
"step": 2690
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.07541530791092614,
|
| 1949 |
+
"grad_norm": 13.747076034545898,
|
| 1950 |
+
"learning_rate": 1.8492263002066923e-06,
|
| 1951 |
+
"loss": 1.3201,
|
| 1952 |
+
"step": 2700
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.07569462386615179,
|
| 1956 |
+
"grad_norm": 10.723194122314453,
|
| 1957 |
+
"learning_rate": 1.848667672197084e-06,
|
| 1958 |
+
"loss": 1.254,
|
| 1959 |
+
"step": 2710
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.07597393982137744,
|
| 1963 |
+
"grad_norm": 11.047980308532715,
|
| 1964 |
+
"learning_rate": 1.8481090441874754e-06,
|
| 1965 |
+
"loss": 1.3657,
|
| 1966 |
+
"step": 2720
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 0.0762532557766031,
|
| 1970 |
+
"grad_norm": 10.199549674987793,
|
| 1971 |
+
"learning_rate": 1.847550416177867e-06,
|
| 1972 |
+
"loss": 1.3775,
|
| 1973 |
+
"step": 2730
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 0.07653257173182876,
|
| 1977 |
+
"grad_norm": 9.60568904876709,
|
| 1978 |
+
"learning_rate": 1.8469917881682586e-06,
|
| 1979 |
+
"loss": 1.3047,
|
| 1980 |
+
"step": 2740
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 0.07681188768705441,
|
| 1984 |
+
"grad_norm": 10.989706993103027,
|
| 1985 |
+
"learning_rate": 1.8464331601586501e-06,
|
| 1986 |
+
"loss": 1.3228,
|
| 1987 |
+
"step": 2750
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 0.07709120364228006,
|
| 1991 |
+
"grad_norm": 12.18575668334961,
|
| 1992 |
+
"learning_rate": 1.845874532149042e-06,
|
| 1993 |
+
"loss": 1.3358,
|
| 1994 |
+
"step": 2760
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.07737051959750571,
|
| 1998 |
+
"grad_norm": 11.24397087097168,
|
| 1999 |
+
"learning_rate": 1.8453159041394335e-06,
|
| 2000 |
+
"loss": 1.3065,
|
| 2001 |
+
"step": 2770
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 0.07764983555273136,
|
| 2005 |
+
"grad_norm": 10.88451862335205,
|
| 2006 |
+
"learning_rate": 1.844757276129825e-06,
|
| 2007 |
+
"loss": 1.3278,
|
| 2008 |
+
"step": 2780
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 0.07792915150795701,
|
| 2012 |
+
"grad_norm": 11.730112075805664,
|
| 2013 |
+
"learning_rate": 1.8441986481202167e-06,
|
| 2014 |
+
"loss": 1.2865,
|
| 2015 |
+
"step": 2790
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 0.07820846746318266,
|
| 2019 |
+
"grad_norm": 11.872193336486816,
|
| 2020 |
+
"learning_rate": 1.8436400201106082e-06,
|
| 2021 |
+
"loss": 1.2728,
|
| 2022 |
+
"step": 2800
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 0.07848778341840831,
|
| 2026 |
+
"grad_norm": 13.440178871154785,
|
| 2027 |
+
"learning_rate": 1.8430813921009998e-06,
|
| 2028 |
+
"loss": 1.3169,
|
| 2029 |
+
"step": 2810
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 0.07876709937363396,
|
| 2033 |
+
"grad_norm": 10.802016258239746,
|
| 2034 |
+
"learning_rate": 1.8425227640913914e-06,
|
| 2035 |
+
"loss": 1.2491,
|
| 2036 |
+
"step": 2820
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 0.07904641532885963,
|
| 2040 |
+
"grad_norm": 11.56015396118164,
|
| 2041 |
+
"learning_rate": 1.841964136081783e-06,
|
| 2042 |
+
"loss": 1.313,
|
| 2043 |
+
"step": 2830
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 0.07932573128408528,
|
| 2047 |
+
"grad_norm": 11.145283699035645,
|
| 2048 |
+
"learning_rate": 1.8414055080721745e-06,
|
| 2049 |
+
"loss": 1.293,
|
| 2050 |
+
"step": 2840
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 0.07960504723931093,
|
| 2054 |
+
"grad_norm": 10.63716983795166,
|
| 2055 |
+
"learning_rate": 1.8408468800625663e-06,
|
| 2056 |
+
"loss": 1.3308,
|
| 2057 |
+
"step": 2850
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 0.07988436319453658,
|
| 2061 |
+
"grad_norm": 11.486001968383789,
|
| 2062 |
+
"learning_rate": 1.840288252052958e-06,
|
| 2063 |
+
"loss": 1.3047,
|
| 2064 |
+
"step": 2860
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 0.08016367914976223,
|
| 2068 |
+
"grad_norm": 10.340072631835938,
|
| 2069 |
+
"learning_rate": 1.8397296240433495e-06,
|
| 2070 |
+
"loss": 1.2763,
|
| 2071 |
+
"step": 2870
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 0.08044299510498788,
|
| 2075 |
+
"grad_norm": 11.177892684936523,
|
| 2076 |
+
"learning_rate": 1.839170996033741e-06,
|
| 2077 |
+
"loss": 1.3218,
|
| 2078 |
+
"step": 2880
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 0.08072231106021353,
|
| 2082 |
+
"grad_norm": 11.822985649108887,
|
| 2083 |
+
"learning_rate": 1.8386123680241326e-06,
|
| 2084 |
+
"loss": 1.3039,
|
| 2085 |
+
"step": 2890
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 0.08100162701543918,
|
| 2089 |
+
"grad_norm": 13.245485305786133,
|
| 2090 |
+
"learning_rate": 1.8380537400145242e-06,
|
| 2091 |
+
"loss": 1.281,
|
| 2092 |
+
"step": 2900
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 0.08128094297066484,
|
| 2096 |
+
"grad_norm": 11.78788948059082,
|
| 2097 |
+
"learning_rate": 1.8374951120049158e-06,
|
| 2098 |
+
"loss": 1.2176,
|
| 2099 |
+
"step": 2910
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 0.0815602589258905,
|
| 2103 |
+
"grad_norm": 11.278291702270508,
|
| 2104 |
+
"learning_rate": 1.8369364839953074e-06,
|
| 2105 |
+
"loss": 1.2972,
|
| 2106 |
+
"step": 2920
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 0.08183957488111615,
|
| 2110 |
+
"grad_norm": 11.119109153747559,
|
| 2111 |
+
"learning_rate": 1.836377855985699e-06,
|
| 2112 |
+
"loss": 1.2689,
|
| 2113 |
+
"step": 2930
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 0.0821188908363418,
|
| 2117 |
+
"grad_norm": 11.489620208740234,
|
| 2118 |
+
"learning_rate": 1.8358192279760907e-06,
|
| 2119 |
+
"loss": 1.3288,
|
| 2120 |
+
"step": 2940
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 0.08239820679156745,
|
| 2124 |
+
"grad_norm": 9.556941032409668,
|
| 2125 |
+
"learning_rate": 1.8352605999664823e-06,
|
| 2126 |
+
"loss": 1.3035,
|
| 2127 |
+
"step": 2950
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 0.0826775227467931,
|
| 2131 |
+
"grad_norm": 11.121188163757324,
|
| 2132 |
+
"learning_rate": 1.8347019719568739e-06,
|
| 2133 |
+
"loss": 1.2944,
|
| 2134 |
+
"step": 2960
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 0.08295683870201875,
|
| 2138 |
+
"grad_norm": 12.729305267333984,
|
| 2139 |
+
"learning_rate": 1.8341433439472653e-06,
|
| 2140 |
+
"loss": 1.3125,
|
| 2141 |
+
"step": 2970
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 0.0832361546572444,
|
| 2145 |
+
"grad_norm": 11.878944396972656,
|
| 2146 |
+
"learning_rate": 1.833584715937657e-06,
|
| 2147 |
+
"loss": 1.2959,
|
| 2148 |
+
"step": 2980
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 0.08351547061247006,
|
| 2152 |
+
"grad_norm": 11.5958833694458,
|
| 2153 |
+
"learning_rate": 1.8330260879280486e-06,
|
| 2154 |
+
"loss": 1.3453,
|
| 2155 |
+
"step": 2990
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 0.08379478656769572,
|
| 2159 |
+
"grad_norm": 12.451947212219238,
|
| 2160 |
+
"learning_rate": 1.8324674599184402e-06,
|
| 2161 |
+
"loss": 1.2819,
|
| 2162 |
+
"step": 3000
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 0.0839623761408311,
|
| 2166 |
+
"eval_complexity_accuracy": 0.0,
|
| 2167 |
+
"eval_loss": 1.3420253992080688,
|
| 2168 |
+
"eval_runtime": 33.8789,
|
| 2169 |
+
"eval_samples_per_second": 14.758,
|
| 2170 |
+
"eval_steps_per_second": 1.86,
|
| 2171 |
+
"step": 3006
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 0.08407410252292137,
|
| 2175 |
+
"grad_norm": 12.807692527770996,
|
| 2176 |
+
"learning_rate": 1.8319088319088318e-06,
|
| 2177 |
+
"loss": 1.3238,
|
| 2178 |
+
"step": 3010
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 0.08435341847814702,
|
| 2182 |
+
"grad_norm": 10.1639404296875,
|
| 2183 |
+
"learning_rate": 1.8313502038992234e-06,
|
| 2184 |
+
"loss": 1.2694,
|
| 2185 |
+
"step": 3020
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 0.08463273443337267,
|
| 2189 |
+
"grad_norm": 11.123089790344238,
|
| 2190 |
+
"learning_rate": 1.8307915758896151e-06,
|
| 2191 |
+
"loss": 1.2404,
|
| 2192 |
+
"step": 3030
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 0.08491205038859832,
|
| 2196 |
+
"grad_norm": 11.976441383361816,
|
| 2197 |
+
"learning_rate": 1.8302329478800067e-06,
|
| 2198 |
+
"loss": 1.3319,
|
| 2199 |
+
"step": 3040
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 0.08519136634382397,
|
| 2203 |
+
"grad_norm": 11.400232315063477,
|
| 2204 |
+
"learning_rate": 1.829674319870398e-06,
|
| 2205 |
+
"loss": 1.2899,
|
| 2206 |
+
"step": 3050
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 0.08547068229904962,
|
| 2210 |
+
"grad_norm": 9.668082237243652,
|
| 2211 |
+
"learning_rate": 1.8291156918607897e-06,
|
| 2212 |
+
"loss": 1.3343,
|
| 2213 |
+
"step": 3060
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 0.08574999825427528,
|
| 2217 |
+
"grad_norm": 9.114018440246582,
|
| 2218 |
+
"learning_rate": 1.8285570638511814e-06,
|
| 2219 |
+
"loss": 1.2822,
|
| 2220 |
+
"step": 3070
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 0.08602931420950093,
|
| 2224 |
+
"grad_norm": 11.763662338256836,
|
| 2225 |
+
"learning_rate": 1.827998435841573e-06,
|
| 2226 |
+
"loss": 1.303,
|
| 2227 |
+
"step": 3080
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 0.08630863016472659,
|
| 2231 |
+
"grad_norm": 12.478301048278809,
|
| 2232 |
+
"learning_rate": 1.8274398078319646e-06,
|
| 2233 |
+
"loss": 1.3204,
|
| 2234 |
+
"step": 3090
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 0.08658794611995224,
|
| 2238 |
+
"grad_norm": 13.733002662658691,
|
| 2239 |
+
"learning_rate": 1.8268811798223562e-06,
|
| 2240 |
+
"loss": 1.2763,
|
| 2241 |
+
"step": 3100
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 0.08686726207517789,
|
| 2245 |
+
"grad_norm": 11.211143493652344,
|
| 2246 |
+
"learning_rate": 1.8263225518127478e-06,
|
| 2247 |
+
"loss": 1.3059,
|
| 2248 |
+
"step": 3110
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 0.08714657803040354,
|
| 2252 |
+
"grad_norm": 10.02708911895752,
|
| 2253 |
+
"learning_rate": 1.8257639238031395e-06,
|
| 2254 |
+
"loss": 1.2576,
|
| 2255 |
+
"step": 3120
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 0.0874258939856292,
|
| 2259 |
+
"grad_norm": 10.271854400634766,
|
| 2260 |
+
"learning_rate": 1.8252052957935311e-06,
|
| 2261 |
+
"loss": 1.3526,
|
| 2262 |
+
"step": 3130
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 0.08770520994085484,
|
| 2266 |
+
"grad_norm": 10.915563583374023,
|
| 2267 |
+
"learning_rate": 1.8246466677839225e-06,
|
| 2268 |
+
"loss": 1.2951,
|
| 2269 |
+
"step": 3140
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 0.0879845258960805,
|
| 2273 |
+
"grad_norm": 12.06615161895752,
|
| 2274 |
+
"learning_rate": 1.824088039774314e-06,
|
| 2275 |
+
"loss": 1.2678,
|
| 2276 |
+
"step": 3150
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 0.08826384185130615,
|
| 2280 |
+
"grad_norm": 11.441333770751953,
|
| 2281 |
+
"learning_rate": 1.8235294117647058e-06,
|
| 2282 |
+
"loss": 1.3605,
|
| 2283 |
+
"step": 3160
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 0.0885431578065318,
|
| 2287 |
+
"grad_norm": 11.135004997253418,
|
| 2288 |
+
"learning_rate": 1.8229707837550974e-06,
|
| 2289 |
+
"loss": 1.3638,
|
| 2290 |
+
"step": 3170
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 0.08882247376175746,
|
| 2294 |
+
"grad_norm": 10.272753715515137,
|
| 2295 |
+
"learning_rate": 1.822412155745489e-06,
|
| 2296 |
+
"loss": 1.3748,
|
| 2297 |
+
"step": 3180
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 0.08910178971698311,
|
| 2301 |
+
"grad_norm": 10.645270347595215,
|
| 2302 |
+
"learning_rate": 1.8218535277358806e-06,
|
| 2303 |
+
"loss": 1.3288,
|
| 2304 |
+
"step": 3190
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.08938110567220876,
|
| 2308 |
+
"grad_norm": 11.341635704040527,
|
| 2309 |
+
"learning_rate": 1.8212948997262722e-06,
|
| 2310 |
+
"loss": 1.3295,
|
| 2311 |
+
"step": 3200
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.08966042162743441,
|
| 2315 |
+
"grad_norm": 11.285005569458008,
|
| 2316 |
+
"learning_rate": 1.820736271716664e-06,
|
| 2317 |
+
"loss": 1.3094,
|
| 2318 |
+
"step": 3210
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.08993973758266006,
|
| 2322 |
+
"grad_norm": 11.092018127441406,
|
| 2323 |
+
"learning_rate": 1.8201776437070553e-06,
|
| 2324 |
+
"loss": 1.2616,
|
| 2325 |
+
"step": 3220
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 0.09021905353788572,
|
| 2329 |
+
"grad_norm": 11.833807945251465,
|
| 2330 |
+
"learning_rate": 1.8196190156974469e-06,
|
| 2331 |
+
"loss": 1.2915,
|
| 2332 |
+
"step": 3230
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 0.09049836949311137,
|
| 2336 |
+
"grad_norm": 11.941621780395508,
|
| 2337 |
+
"learning_rate": 1.8190603876878385e-06,
|
| 2338 |
+
"loss": 1.2984,
|
| 2339 |
+
"step": 3240
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 0.09077768544833702,
|
| 2343 |
+
"grad_norm": 11.135613441467285,
|
| 2344 |
+
"learning_rate": 1.8185017596782303e-06,
|
| 2345 |
+
"loss": 1.2638,
|
| 2346 |
+
"step": 3250
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 0.09105700140356268,
|
| 2350 |
+
"grad_norm": 11.356342315673828,
|
| 2351 |
+
"learning_rate": 1.8179431316686218e-06,
|
| 2352 |
+
"loss": 1.3199,
|
| 2353 |
+
"step": 3260
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 0.09133631735878833,
|
| 2357 |
+
"grad_norm": 11.519587516784668,
|
| 2358 |
+
"learning_rate": 1.8173845036590134e-06,
|
| 2359 |
+
"loss": 1.288,
|
| 2360 |
+
"step": 3270
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 0.09161563331401398,
|
| 2364 |
+
"grad_norm": 11.335143089294434,
|
| 2365 |
+
"learning_rate": 1.816825875649405e-06,
|
| 2366 |
+
"loss": 1.2472,
|
| 2367 |
+
"step": 3280
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 0.09189494926923963,
|
| 2371 |
+
"grad_norm": 12.195459365844727,
|
| 2372 |
+
"learning_rate": 1.8162672476397966e-06,
|
| 2373 |
+
"loss": 1.2992,
|
| 2374 |
+
"step": 3290
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 0.09217426522446528,
|
| 2378 |
+
"grad_norm": 12.05800724029541,
|
| 2379 |
+
"learning_rate": 1.8157086196301881e-06,
|
| 2380 |
+
"loss": 1.3177,
|
| 2381 |
+
"step": 3300
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 0.09245358117969094,
|
| 2385 |
+
"grad_norm": 10.606769561767578,
|
| 2386 |
+
"learning_rate": 1.8151499916205797e-06,
|
| 2387 |
+
"loss": 1.2693,
|
| 2388 |
+
"step": 3310
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 0.09273289713491659,
|
| 2392 |
+
"grad_norm": 9.679693222045898,
|
| 2393 |
+
"learning_rate": 1.8145913636109713e-06,
|
| 2394 |
+
"loss": 1.2985,
|
| 2395 |
+
"step": 3320
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 0.09301221309014224,
|
| 2399 |
+
"grad_norm": 10.03492546081543,
|
| 2400 |
+
"learning_rate": 1.8140327356013629e-06,
|
| 2401 |
+
"loss": 1.2724,
|
| 2402 |
+
"step": 3330
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 0.09329152904536789,
|
| 2406 |
+
"grad_norm": 10.985275268554688,
|
| 2407 |
+
"learning_rate": 1.8134741075917547e-06,
|
| 2408 |
+
"loss": 1.2551,
|
| 2409 |
+
"step": 3340
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.09357084500059355,
|
| 2413 |
+
"grad_norm": 11.815603256225586,
|
| 2414 |
+
"learning_rate": 1.8129154795821462e-06,
|
| 2415 |
+
"loss": 1.3062,
|
| 2416 |
+
"step": 3350
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 0.0938501609558192,
|
| 2420 |
+
"grad_norm": 10.699769020080566,
|
| 2421 |
+
"learning_rate": 1.8123568515725378e-06,
|
| 2422 |
+
"loss": 1.2841,
|
| 2423 |
+
"step": 3360
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 0.09412947691104485,
|
| 2427 |
+
"grad_norm": 12.014618873596191,
|
| 2428 |
+
"learning_rate": 1.8117982235629294e-06,
|
| 2429 |
+
"loss": 1.3132,
|
| 2430 |
+
"step": 3370
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 0.0944087928662705,
|
| 2434 |
+
"grad_norm": 11.724242210388184,
|
| 2435 |
+
"learning_rate": 1.811239595553321e-06,
|
| 2436 |
+
"loss": 1.289,
|
| 2437 |
+
"step": 3380
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 0.09468810882149616,
|
| 2441 |
+
"grad_norm": 12.180294036865234,
|
| 2442 |
+
"learning_rate": 1.8106809675437125e-06,
|
| 2443 |
+
"loss": 1.3496,
|
| 2444 |
+
"step": 3390
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 0.0949674247767218,
|
| 2448 |
+
"grad_norm": 10.988664627075195,
|
| 2449 |
+
"learning_rate": 1.8101223395341041e-06,
|
| 2450 |
+
"loss": 1.3244,
|
| 2451 |
+
"step": 3400
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 0.09524674073194746,
|
| 2455 |
+
"grad_norm": 12.344855308532715,
|
| 2456 |
+
"learning_rate": 1.8095637115244957e-06,
|
| 2457 |
+
"loss": 1.2996,
|
| 2458 |
+
"step": 3410
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 0.09552605668717311,
|
| 2462 |
+
"grad_norm": 10.685724258422852,
|
| 2463 |
+
"learning_rate": 1.8090050835148873e-06,
|
| 2464 |
+
"loss": 1.261,
|
| 2465 |
+
"step": 3420
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 0.09580537264239876,
|
| 2469 |
+
"grad_norm": 12.516709327697754,
|
| 2470 |
+
"learning_rate": 1.808446455505279e-06,
|
| 2471 |
+
"loss": 1.2756,
|
| 2472 |
+
"step": 3430
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 0.09608468859762442,
|
| 2476 |
+
"grad_norm": 11.27023983001709,
|
| 2477 |
+
"learning_rate": 1.8078878274956706e-06,
|
| 2478 |
+
"loss": 1.2935,
|
| 2479 |
+
"step": 3440
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 0.09636400455285007,
|
| 2483 |
+
"grad_norm": 12.012152671813965,
|
| 2484 |
+
"learning_rate": 1.8073291994860622e-06,
|
| 2485 |
+
"loss": 1.317,
|
| 2486 |
+
"step": 3450
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.09664332050807573,
|
| 2490 |
+
"grad_norm": 11.254688262939453,
|
| 2491 |
+
"learning_rate": 1.8067705714764538e-06,
|
| 2492 |
+
"loss": 1.3272,
|
| 2493 |
+
"step": 3460
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 0.09692263646330138,
|
| 2497 |
+
"grad_norm": 12.010251998901367,
|
| 2498 |
+
"learning_rate": 1.8062119434668452e-06,
|
| 2499 |
+
"loss": 1.3732,
|
| 2500 |
+
"step": 3470
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 0.09720195241852703,
|
| 2504 |
+
"grad_norm": 12.29020881652832,
|
| 2505 |
+
"learning_rate": 1.805653315457237e-06,
|
| 2506 |
+
"loss": 1.2978,
|
| 2507 |
+
"step": 3480
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 0.09748126837375268,
|
| 2511 |
+
"grad_norm": 12.708207130432129,
|
| 2512 |
+
"learning_rate": 1.8050946874476285e-06,
|
| 2513 |
+
"loss": 1.3173,
|
| 2514 |
+
"step": 3490
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 0.09776058432897833,
|
| 2518 |
+
"grad_norm": 11.069357872009277,
|
| 2519 |
+
"learning_rate": 1.80453605943802e-06,
|
| 2520 |
+
"loss": 1.3188,
|
| 2521 |
+
"step": 3500
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 0.0979561054976363,
|
| 2525 |
+
"eval_complexity_accuracy": 0.0,
|
| 2526 |
+
"eval_loss": 1.3392640352249146,
|
| 2527 |
+
"eval_runtime": 34.0525,
|
| 2528 |
+
"eval_samples_per_second": 14.683,
|
| 2529 |
+
"eval_steps_per_second": 1.85,
|
| 2530 |
+
"step": 3507
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.09803990028420398,
|
| 2534 |
+
"grad_norm": 13.221611976623535,
|
| 2535 |
+
"learning_rate": 1.8039774314284117e-06,
|
| 2536 |
+
"loss": 1.2449,
|
| 2537 |
+
"step": 3510
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.09831921623942964,
|
| 2541 |
+
"grad_norm": 11.22923755645752,
|
| 2542 |
+
"learning_rate": 1.8034188034188035e-06,
|
| 2543 |
+
"loss": 1.3242,
|
| 2544 |
+
"step": 3520
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.0985985321946553,
|
| 2548 |
+
"grad_norm": 10.731654167175293,
|
| 2549 |
+
"learning_rate": 1.802860175409195e-06,
|
| 2550 |
+
"loss": 1.363,
|
| 2551 |
+
"step": 3530
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.09887784814988095,
|
| 2555 |
+
"grad_norm": 11.269989967346191,
|
| 2556 |
+
"learning_rate": 1.8023015473995866e-06,
|
| 2557 |
+
"loss": 1.2708,
|
| 2558 |
+
"step": 3540
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.0991571641051066,
|
| 2562 |
+
"grad_norm": 10.26361083984375,
|
| 2563 |
+
"learning_rate": 1.801742919389978e-06,
|
| 2564 |
+
"loss": 1.3219,
|
| 2565 |
+
"step": 3550
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.09943648006033225,
|
| 2569 |
+
"grad_norm": 10.341995239257812,
|
| 2570 |
+
"learning_rate": 1.8011842913803696e-06,
|
| 2571 |
+
"loss": 1.2953,
|
| 2572 |
+
"step": 3560
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.0997157960155579,
|
| 2576 |
+
"grad_norm": 10.96583080291748,
|
| 2577 |
+
"learning_rate": 1.8006256633707613e-06,
|
| 2578 |
+
"loss": 1.3132,
|
| 2579 |
+
"step": 3570
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.09999511197078355,
|
| 2583 |
+
"grad_norm": 11.878289222717285,
|
| 2584 |
+
"learning_rate": 1.800067035361153e-06,
|
| 2585 |
+
"loss": 1.3109,
|
| 2586 |
+
"step": 3580
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.1002744279260092,
|
| 2590 |
+
"grad_norm": 9.536112785339355,
|
| 2591 |
+
"learning_rate": 1.7995084073515445e-06,
|
| 2592 |
+
"loss": 1.3468,
|
| 2593 |
+
"step": 3590
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.10055374388123485,
|
| 2597 |
+
"grad_norm": 10.972228050231934,
|
| 2598 |
+
"learning_rate": 1.798949779341936e-06,
|
| 2599 |
+
"loss": 1.2877,
|
| 2600 |
+
"step": 3600
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.10083305983646051,
|
| 2604 |
+
"grad_norm": 13.208352088928223,
|
| 2605 |
+
"learning_rate": 1.7983911513323279e-06,
|
| 2606 |
+
"loss": 1.3701,
|
| 2607 |
+
"step": 3610
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.10111237579168617,
|
| 2611 |
+
"grad_norm": 11.069518089294434,
|
| 2612 |
+
"learning_rate": 1.7978325233227194e-06,
|
| 2613 |
+
"loss": 1.2269,
|
| 2614 |
+
"step": 3620
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.10139169174691182,
|
| 2618 |
+
"grad_norm": 11.275925636291504,
|
| 2619 |
+
"learning_rate": 1.797273895313111e-06,
|
| 2620 |
+
"loss": 1.3039,
|
| 2621 |
+
"step": 3630
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.10167100770213747,
|
| 2625 |
+
"grad_norm": 9.614294052124023,
|
| 2626 |
+
"learning_rate": 1.7967152673035024e-06,
|
| 2627 |
+
"loss": 1.2987,
|
| 2628 |
+
"step": 3640
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.10195032365736312,
|
| 2632 |
+
"grad_norm": 11.417302131652832,
|
| 2633 |
+
"learning_rate": 1.796156639293894e-06,
|
| 2634 |
+
"loss": 1.3161,
|
| 2635 |
+
"step": 3650
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.10222963961258877,
|
| 2639 |
+
"grad_norm": 13.481733322143555,
|
| 2640 |
+
"learning_rate": 1.7955980112842857e-06,
|
| 2641 |
+
"loss": 1.277,
|
| 2642 |
+
"step": 3660
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.10250895556781442,
|
| 2646 |
+
"grad_norm": 12.135738372802734,
|
| 2647 |
+
"learning_rate": 1.7950393832746773e-06,
|
| 2648 |
+
"loss": 1.3031,
|
| 2649 |
+
"step": 3670
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.10278827152304007,
|
| 2653 |
+
"grad_norm": 11.81387710571289,
|
| 2654 |
+
"learning_rate": 1.794480755265069e-06,
|
| 2655 |
+
"loss": 1.3195,
|
| 2656 |
+
"step": 3680
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.10306758747826572,
|
| 2660 |
+
"grad_norm": 12.341436386108398,
|
| 2661 |
+
"learning_rate": 1.7939221272554605e-06,
|
| 2662 |
+
"loss": 1.344,
|
| 2663 |
+
"step": 3690
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.10334690343349139,
|
| 2667 |
+
"grad_norm": 11.813607215881348,
|
| 2668 |
+
"learning_rate": 1.7933634992458523e-06,
|
| 2669 |
+
"loss": 1.2456,
|
| 2670 |
+
"step": 3700
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.10362621938871704,
|
| 2674 |
+
"grad_norm": 10.025679588317871,
|
| 2675 |
+
"learning_rate": 1.7928048712362438e-06,
|
| 2676 |
+
"loss": 1.3462,
|
| 2677 |
+
"step": 3710
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.10390553534394269,
|
| 2681 |
+
"grad_norm": 11.027300834655762,
|
| 2682 |
+
"learning_rate": 1.7922462432266352e-06,
|
| 2683 |
+
"loss": 1.248,
|
| 2684 |
+
"step": 3720
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.10418485129916834,
|
| 2688 |
+
"grad_norm": 10.462127685546875,
|
| 2689 |
+
"learning_rate": 1.7916876152170268e-06,
|
| 2690 |
+
"loss": 1.2827,
|
| 2691 |
+
"step": 3730
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.10446416725439399,
|
| 2695 |
+
"grad_norm": 11.07565689086914,
|
| 2696 |
+
"learning_rate": 1.7911289872074184e-06,
|
| 2697 |
+
"loss": 1.3317,
|
| 2698 |
+
"step": 3740
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.10474348320961964,
|
| 2702 |
+
"grad_norm": 10.2979097366333,
|
| 2703 |
+
"learning_rate": 1.7905703591978101e-06,
|
| 2704 |
+
"loss": 1.2484,
|
| 2705 |
+
"step": 3750
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.10502279916484529,
|
| 2709 |
+
"grad_norm": 11.009065628051758,
|
| 2710 |
+
"learning_rate": 1.7900117311882017e-06,
|
| 2711 |
+
"loss": 1.2882,
|
| 2712 |
+
"step": 3760
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.10530211512007094,
|
| 2716 |
+
"grad_norm": 11.308358192443848,
|
| 2717 |
+
"learning_rate": 1.7894531031785933e-06,
|
| 2718 |
+
"loss": 1.3095,
|
| 2719 |
+
"step": 3770
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.10558143107529659,
|
| 2723 |
+
"grad_norm": 11.058066368103027,
|
| 2724 |
+
"learning_rate": 1.7888944751689849e-06,
|
| 2725 |
+
"loss": 1.3372,
|
| 2726 |
+
"step": 3780
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.10586074703052226,
|
| 2730 |
+
"grad_norm": 13.103239059448242,
|
| 2731 |
+
"learning_rate": 1.7883358471593767e-06,
|
| 2732 |
+
"loss": 1.3124,
|
| 2733 |
+
"step": 3790
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.10614006298574791,
|
| 2737 |
+
"grad_norm": 10.5227689743042,
|
| 2738 |
+
"learning_rate": 1.787777219149768e-06,
|
| 2739 |
+
"loss": 1.2608,
|
| 2740 |
+
"step": 3800
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.10641937894097356,
|
| 2744 |
+
"grad_norm": 10.993918418884277,
|
| 2745 |
+
"learning_rate": 1.7872185911401596e-06,
|
| 2746 |
+
"loss": 1.259,
|
| 2747 |
+
"step": 3810
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.10669869489619921,
|
| 2751 |
+
"grad_norm": 11.612725257873535,
|
| 2752 |
+
"learning_rate": 1.7866599631305512e-06,
|
| 2753 |
+
"loss": 1.3046,
|
| 2754 |
+
"step": 3820
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.10697801085142486,
|
| 2758 |
+
"grad_norm": 11.200050354003906,
|
| 2759 |
+
"learning_rate": 1.7861013351209428e-06,
|
| 2760 |
+
"loss": 1.3439,
|
| 2761 |
+
"step": 3830
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.10725732680665051,
|
| 2765 |
+
"grad_norm": 12.19509220123291,
|
| 2766 |
+
"learning_rate": 1.7855427071113346e-06,
|
| 2767 |
+
"loss": 1.3107,
|
| 2768 |
+
"step": 3840
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.10753664276187616,
|
| 2772 |
+
"grad_norm": 11.498516082763672,
|
| 2773 |
+
"learning_rate": 1.7849840791017261e-06,
|
| 2774 |
+
"loss": 1.3341,
|
| 2775 |
+
"step": 3850
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.10781595871710181,
|
| 2779 |
+
"grad_norm": 12.180155754089355,
|
| 2780 |
+
"learning_rate": 1.7844254510921177e-06,
|
| 2781 |
+
"loss": 1.2753,
|
| 2782 |
+
"step": 3860
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.10809527467232748,
|
| 2786 |
+
"grad_norm": 10.637706756591797,
|
| 2787 |
+
"learning_rate": 1.7838668230825093e-06,
|
| 2788 |
+
"loss": 1.2221,
|
| 2789 |
+
"step": 3870
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.10837459062755313,
|
| 2793 |
+
"grad_norm": 11.029936790466309,
|
| 2794 |
+
"learning_rate": 1.783308195072901e-06,
|
| 2795 |
+
"loss": 1.3397,
|
| 2796 |
+
"step": 3880
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.10865390658277878,
|
| 2800 |
+
"grad_norm": 9.736263275146484,
|
| 2801 |
+
"learning_rate": 1.7827495670632924e-06,
|
| 2802 |
+
"loss": 1.339,
|
| 2803 |
+
"step": 3890
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.10893322253800443,
|
| 2807 |
+
"grad_norm": 11.16982364654541,
|
| 2808 |
+
"learning_rate": 1.782190939053684e-06,
|
| 2809 |
+
"loss": 1.3309,
|
| 2810 |
+
"step": 3900
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.10921253849323008,
|
| 2814 |
+
"grad_norm": 10.91207218170166,
|
| 2815 |
+
"learning_rate": 1.7816323110440756e-06,
|
| 2816 |
+
"loss": 1.2543,
|
| 2817 |
+
"step": 3910
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.10949185444845573,
|
| 2821 |
+
"grad_norm": 14.678290367126465,
|
| 2822 |
+
"learning_rate": 1.7810736830344672e-06,
|
| 2823 |
+
"loss": 1.355,
|
| 2824 |
+
"step": 3920
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.10977117040368138,
|
| 2828 |
+
"grad_norm": 11.110123634338379,
|
| 2829 |
+
"learning_rate": 1.780515055024859e-06,
|
| 2830 |
+
"loss": 1.251,
|
| 2831 |
+
"step": 3930
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.11005048635890703,
|
| 2835 |
+
"grad_norm": 11.788151741027832,
|
| 2836 |
+
"learning_rate": 1.7799564270152505e-06,
|
| 2837 |
+
"loss": 1.2544,
|
| 2838 |
+
"step": 3940
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.11032980231413268,
|
| 2842 |
+
"grad_norm": 10.897525787353516,
|
| 2843 |
+
"learning_rate": 1.7793977990056421e-06,
|
| 2844 |
+
"loss": 1.2932,
|
| 2845 |
+
"step": 3950
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.11060911826935835,
|
| 2849 |
+
"grad_norm": 12.554097175598145,
|
| 2850 |
+
"learning_rate": 1.7788391709960337e-06,
|
| 2851 |
+
"loss": 1.3412,
|
| 2852 |
+
"step": 3960
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.110888434224584,
|
| 2856 |
+
"grad_norm": 11.195846557617188,
|
| 2857 |
+
"learning_rate": 1.7782805429864253e-06,
|
| 2858 |
+
"loss": 1.311,
|
| 2859 |
+
"step": 3970
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.11116775017980965,
|
| 2863 |
+
"grad_norm": 11.825657844543457,
|
| 2864 |
+
"learning_rate": 1.7777219149768168e-06,
|
| 2865 |
+
"loss": 1.2449,
|
| 2866 |
+
"step": 3980
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.1114470661350353,
|
| 2870 |
+
"grad_norm": 11.154561996459961,
|
| 2871 |
+
"learning_rate": 1.7771632869672084e-06,
|
| 2872 |
+
"loss": 1.2969,
|
| 2873 |
+
"step": 3990
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.11172638209026095,
|
| 2877 |
+
"grad_norm": 12.427309036254883,
|
| 2878 |
+
"learning_rate": 1.7766046589576e-06,
|
| 2879 |
+
"loss": 1.3205,
|
| 2880 |
+
"step": 4000
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.11194983485444147,
|
| 2884 |
+
"eval_complexity_accuracy": 0.0,
|
| 2885 |
+
"eval_loss": 1.337980031967163,
|
| 2886 |
+
"eval_runtime": 33.7197,
|
| 2887 |
+
"eval_samples_per_second": 14.828,
|
| 2888 |
+
"eval_steps_per_second": 1.868,
|
| 2889 |
+
"step": 4008
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 0.1120056980454866,
|
| 2893 |
+
"grad_norm": 11.303837776184082,
|
| 2894 |
+
"learning_rate": 1.7760460309479916e-06,
|
| 2895 |
+
"loss": 1.2941,
|
| 2896 |
+
"step": 4010
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.11228501400071225,
|
| 2900 |
+
"grad_norm": 10.283913612365723,
|
| 2901 |
+
"learning_rate": 1.7754874029383834e-06,
|
| 2902 |
+
"loss": 1.2637,
|
| 2903 |
+
"step": 4020
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 0.1125643299559379,
|
| 2907 |
+
"grad_norm": 9.881290435791016,
|
| 2908 |
+
"learning_rate": 1.774928774928775e-06,
|
| 2909 |
+
"loss": 1.2764,
|
| 2910 |
+
"step": 4030
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 0.11284364591116355,
|
| 2914 |
+
"grad_norm": 10.254637718200684,
|
| 2915 |
+
"learning_rate": 1.7743701469191665e-06,
|
| 2916 |
+
"loss": 1.3215,
|
| 2917 |
+
"step": 4040
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 0.11312296186638922,
|
| 2921 |
+
"grad_norm": 11.556249618530273,
|
| 2922 |
+
"learning_rate": 1.7738115189095579e-06,
|
| 2923 |
+
"loss": 1.3581,
|
| 2924 |
+
"step": 4050
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.11340227782161487,
|
| 2928 |
+
"grad_norm": 11.59968376159668,
|
| 2929 |
+
"learning_rate": 1.7732528908999497e-06,
|
| 2930 |
+
"loss": 1.3089,
|
| 2931 |
+
"step": 4060
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 0.11368159377684052,
|
| 2935 |
+
"grad_norm": 11.252206802368164,
|
| 2936 |
+
"learning_rate": 1.7726942628903412e-06,
|
| 2937 |
+
"loss": 1.242,
|
| 2938 |
+
"step": 4070
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 0.11396090973206617,
|
| 2942 |
+
"grad_norm": 10.428114891052246,
|
| 2943 |
+
"learning_rate": 1.7721356348807328e-06,
|
| 2944 |
+
"loss": 1.3395,
|
| 2945 |
+
"step": 4080
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 0.11424022568729182,
|
| 2949 |
+
"grad_norm": 12.992630958557129,
|
| 2950 |
+
"learning_rate": 1.7715770068711244e-06,
|
| 2951 |
+
"loss": 1.305,
|
| 2952 |
+
"step": 4090
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 0.11451954164251747,
|
| 2956 |
+
"grad_norm": 10.460079193115234,
|
| 2957 |
+
"learning_rate": 1.771018378861516e-06,
|
| 2958 |
+
"loss": 1.2225,
|
| 2959 |
+
"step": 4100
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 0.11479885759774312,
|
| 2963 |
+
"grad_norm": 10.601390838623047,
|
| 2964 |
+
"learning_rate": 1.7704597508519078e-06,
|
| 2965 |
+
"loss": 1.3129,
|
| 2966 |
+
"step": 4110
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.11507817355296877,
|
| 2970 |
+
"grad_norm": 13.683563232421875,
|
| 2971 |
+
"learning_rate": 1.7699011228422993e-06,
|
| 2972 |
+
"loss": 1.3081,
|
| 2973 |
+
"step": 4120
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 0.11535748950819444,
|
| 2977 |
+
"grad_norm": 12.05490493774414,
|
| 2978 |
+
"learning_rate": 1.769342494832691e-06,
|
| 2979 |
+
"loss": 1.2893,
|
| 2980 |
+
"step": 4130
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 0.11563680546342009,
|
| 2984 |
+
"grad_norm": 10.546974182128906,
|
| 2985 |
+
"learning_rate": 1.7687838668230823e-06,
|
| 2986 |
+
"loss": 1.3494,
|
| 2987 |
+
"step": 4140
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 0.11591612141864574,
|
| 2991 |
+
"grad_norm": 11.625492095947266,
|
| 2992 |
+
"learning_rate": 1.768225238813474e-06,
|
| 2993 |
+
"loss": 1.2876,
|
| 2994 |
+
"step": 4150
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 0.11619543737387139,
|
| 2998 |
+
"grad_norm": 11.499431610107422,
|
| 2999 |
+
"learning_rate": 1.7676666108038656e-06,
|
| 3000 |
+
"loss": 1.2298,
|
| 3001 |
+
"step": 4160
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 0.11647475332909704,
|
| 3005 |
+
"grad_norm": 10.968666076660156,
|
| 3006 |
+
"learning_rate": 1.7671079827942572e-06,
|
| 3007 |
+
"loss": 1.3229,
|
| 3008 |
+
"step": 4170
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 0.11675406928432269,
|
| 3012 |
+
"grad_norm": 10.56057071685791,
|
| 3013 |
+
"learning_rate": 1.7665493547846488e-06,
|
| 3014 |
+
"loss": 1.2644,
|
| 3015 |
+
"step": 4180
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 0.11703338523954834,
|
| 3019 |
+
"grad_norm": 10.645150184631348,
|
| 3020 |
+
"learning_rate": 1.7659907267750404e-06,
|
| 3021 |
+
"loss": 1.3216,
|
| 3022 |
+
"step": 4190
|
| 3023 |
+
},
|
| 3024 |
+
{
|
| 3025 |
+
"epoch": 0.117312701194774,
|
| 3026 |
+
"grad_norm": 10.945796966552734,
|
| 3027 |
+
"learning_rate": 1.7654320987654322e-06,
|
| 3028 |
+
"loss": 1.3395,
|
| 3029 |
+
"step": 4200
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 0.11759201714999964,
|
| 3033 |
+
"grad_norm": 11.30075740814209,
|
| 3034 |
+
"learning_rate": 1.7648734707558237e-06,
|
| 3035 |
+
"loss": 1.3201,
|
| 3036 |
+
"step": 4210
|
| 3037 |
+
},
|
| 3038 |
+
{
|
| 3039 |
+
"epoch": 0.11787133310522531,
|
| 3040 |
+
"grad_norm": 11.912382125854492,
|
| 3041 |
+
"learning_rate": 1.764314842746215e-06,
|
| 3042 |
+
"loss": 1.3076,
|
| 3043 |
+
"step": 4220
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 0.11815064906045096,
|
| 3047 |
+
"grad_norm": 11.546857833862305,
|
| 3048 |
+
"learning_rate": 1.7637562147366067e-06,
|
| 3049 |
+
"loss": 1.2776,
|
| 3050 |
+
"step": 4230
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 0.11842996501567661,
|
| 3054 |
+
"grad_norm": 11.775701522827148,
|
| 3055 |
+
"learning_rate": 1.7631975867269985e-06,
|
| 3056 |
+
"loss": 1.3094,
|
| 3057 |
+
"step": 4240
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 0.11870928097090226,
|
| 3061 |
+
"grad_norm": 11.965110778808594,
|
| 3062 |
+
"learning_rate": 1.76263895871739e-06,
|
| 3063 |
+
"loss": 1.2815,
|
| 3064 |
+
"step": 4250
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 0.11898859692612791,
|
| 3068 |
+
"grad_norm": 9.932812690734863,
|
| 3069 |
+
"learning_rate": 1.7620803307077816e-06,
|
| 3070 |
+
"loss": 1.2965,
|
| 3071 |
+
"step": 4260
|
| 3072 |
+
},
|
| 3073 |
+
{
|
| 3074 |
+
"epoch": 0.11926791288135356,
|
| 3075 |
+
"grad_norm": 10.788895606994629,
|
| 3076 |
+
"learning_rate": 1.7615217026981732e-06,
|
| 3077 |
+
"loss": 1.3025,
|
| 3078 |
+
"step": 4270
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"epoch": 0.11954722883657921,
|
| 3082 |
+
"grad_norm": 12.008225440979004,
|
| 3083 |
+
"learning_rate": 1.7609630746885648e-06,
|
| 3084 |
+
"loss": 1.2758,
|
| 3085 |
+
"step": 4280
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 0.11982654479180486,
|
| 3089 |
+
"grad_norm": 11.157905578613281,
|
| 3090 |
+
"learning_rate": 1.7604044466789566e-06,
|
| 3091 |
+
"loss": 1.3369,
|
| 3092 |
+
"step": 4290
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 0.12010586074703052,
|
| 3096 |
+
"grad_norm": 12.967375755310059,
|
| 3097 |
+
"learning_rate": 1.759845818669348e-06,
|
| 3098 |
+
"loss": 1.3124,
|
| 3099 |
+
"step": 4300
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 0.12038517670225618,
|
| 3103 |
+
"grad_norm": 13.764420509338379,
|
| 3104 |
+
"learning_rate": 1.7592871906597395e-06,
|
| 3105 |
+
"loss": 1.3243,
|
| 3106 |
+
"step": 4310
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 0.12066449265748183,
|
| 3110 |
+
"grad_norm": 11.486067771911621,
|
| 3111 |
+
"learning_rate": 1.758728562650131e-06,
|
| 3112 |
+
"loss": 1.2865,
|
| 3113 |
+
"step": 4320
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 0.12094380861270748,
|
| 3117 |
+
"grad_norm": 11.377238273620605,
|
| 3118 |
+
"learning_rate": 1.7581699346405229e-06,
|
| 3119 |
+
"loss": 1.2747,
|
| 3120 |
+
"step": 4330
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 0.12122312456793313,
|
| 3124 |
+
"grad_norm": 11.644318580627441,
|
| 3125 |
+
"learning_rate": 1.7576113066309144e-06,
|
| 3126 |
+
"loss": 1.2855,
|
| 3127 |
+
"step": 4340
|
| 3128 |
+
},
|
| 3129 |
+
{
|
| 3130 |
+
"epoch": 0.12150244052315878,
|
| 3131 |
+
"grad_norm": 11.282743453979492,
|
| 3132 |
+
"learning_rate": 1.757052678621306e-06,
|
| 3133 |
+
"loss": 1.2109,
|
| 3134 |
+
"step": 4350
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 0.12178175647838443,
|
| 3138 |
+
"grad_norm": 10.718985557556152,
|
| 3139 |
+
"learning_rate": 1.7564940506116976e-06,
|
| 3140 |
+
"loss": 1.3098,
|
| 3141 |
+
"step": 4360
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"epoch": 0.12206107243361008,
|
| 3145 |
+
"grad_norm": 10.54099178314209,
|
| 3146 |
+
"learning_rate": 1.7559354226020892e-06,
|
| 3147 |
+
"loss": 1.2253,
|
| 3148 |
+
"step": 4370
|
| 3149 |
+
},
|
| 3150 |
+
{
|
| 3151 |
+
"epoch": 0.12234038838883574,
|
| 3152 |
+
"grad_norm": 10.001184463500977,
|
| 3153 |
+
"learning_rate": 1.755376794592481e-06,
|
| 3154 |
+
"loss": 1.3096,
|
| 3155 |
+
"step": 4380
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 0.1226197043440614,
|
| 3159 |
+
"grad_norm": 10.10665512084961,
|
| 3160 |
+
"learning_rate": 1.7548181665828723e-06,
|
| 3161 |
+
"loss": 1.3204,
|
| 3162 |
+
"step": 4390
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 0.12289902029928705,
|
| 3166 |
+
"grad_norm": 13.317100524902344,
|
| 3167 |
+
"learning_rate": 1.754259538573264e-06,
|
| 3168 |
+
"loss": 1.2701,
|
| 3169 |
+
"step": 4400
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 0.1231783362545127,
|
| 3173 |
+
"grad_norm": 10.948107719421387,
|
| 3174 |
+
"learning_rate": 1.7537009105636555e-06,
|
| 3175 |
+
"loss": 1.3417,
|
| 3176 |
+
"step": 4410
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 0.12345765220973835,
|
| 3180 |
+
"grad_norm": 11.12563705444336,
|
| 3181 |
+
"learning_rate": 1.7531422825540473e-06,
|
| 3182 |
+
"loss": 1.2768,
|
| 3183 |
+
"step": 4420
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 0.123736968164964,
|
| 3187 |
+
"grad_norm": 11.270187377929688,
|
| 3188 |
+
"learning_rate": 1.7525836545444389e-06,
|
| 3189 |
+
"loss": 1.2476,
|
| 3190 |
+
"step": 4430
|
| 3191 |
+
},
|
| 3192 |
+
{
|
| 3193 |
+
"epoch": 0.12401628412018965,
|
| 3194 |
+
"grad_norm": 11.370152473449707,
|
| 3195 |
+
"learning_rate": 1.7520250265348304e-06,
|
| 3196 |
+
"loss": 1.3711,
|
| 3197 |
+
"step": 4440
|
| 3198 |
+
},
|
| 3199 |
+
{
|
| 3200 |
+
"epoch": 0.1242956000754153,
|
| 3201 |
+
"grad_norm": 12.357138633728027,
|
| 3202 |
+
"learning_rate": 1.751466398525222e-06,
|
| 3203 |
+
"loss": 1.2697,
|
| 3204 |
+
"step": 4450
|
| 3205 |
+
},
|
| 3206 |
+
{
|
| 3207 |
+
"epoch": 0.12457491603064096,
|
| 3208 |
+
"grad_norm": 10.51325511932373,
|
| 3209 |
+
"learning_rate": 1.7509077705156136e-06,
|
| 3210 |
+
"loss": 1.3495,
|
| 3211 |
+
"step": 4460
|
| 3212 |
+
},
|
| 3213 |
+
{
|
| 3214 |
+
"epoch": 0.1248542319858666,
|
| 3215 |
+
"grad_norm": 14.585171699523926,
|
| 3216 |
+
"learning_rate": 1.7503491425060052e-06,
|
| 3217 |
+
"loss": 1.3023,
|
| 3218 |
+
"step": 4470
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 0.12513354794109227,
|
| 3222 |
+
"grad_norm": 11.234824180603027,
|
| 3223 |
+
"learning_rate": 1.7497905144963967e-06,
|
| 3224 |
+
"loss": 1.2785,
|
| 3225 |
+
"step": 4480
|
| 3226 |
+
},
|
| 3227 |
+
{
|
| 3228 |
+
"epoch": 0.12541286389631792,
|
| 3229 |
+
"grad_norm": 10.963340759277344,
|
| 3230 |
+
"learning_rate": 1.7492318864867883e-06,
|
| 3231 |
+
"loss": 1.3196,
|
| 3232 |
+
"step": 4490
|
| 3233 |
+
},
|
| 3234 |
+
{
|
| 3235 |
+
"epoch": 0.12569217985154357,
|
| 3236 |
+
"grad_norm": 10.97410774230957,
|
| 3237 |
+
"learning_rate": 1.7486732584771799e-06,
|
| 3238 |
+
"loss": 1.3396,
|
| 3239 |
+
"step": 4500
|
| 3240 |
+
}
|
| 3241 |
+
],
|
| 3242 |
+
"logging_steps": 10,
|
| 3243 |
+
"max_steps": 35802,
|
| 3244 |
+
"num_input_tokens_seen": 0,
|
| 3245 |
+
"num_train_epochs": 1,
|
| 3246 |
+
"save_steps": 500,
|
| 3247 |
+
"stateful_callbacks": {
|
| 3248 |
+
"TrainerControl": {
|
| 3249 |
+
"args": {
|
| 3250 |
+
"should_epoch_stop": false,
|
| 3251 |
+
"should_evaluate": false,
|
| 3252 |
+
"should_log": false,
|
| 3253 |
+
"should_save": true,
|
| 3254 |
+
"should_training_stop": false
|
| 3255 |
+
},
|
| 3256 |
+
"attributes": {}
|
| 3257 |
+
}
|
| 3258 |
+
},
|
| 3259 |
+
"total_flos": 0.0,
|
| 3260 |
+
"train_batch_size": 2,
|
| 3261 |
+
"trial_name": null,
|
| 3262 |
+
"trial_params": null
|
| 3263 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:502b3584797050cd50e95827a7d25e7c23ffc6ce1e17d46a8eb31367ddba8abf
|
| 3 |
+
size 5969
|