Auto upload zain 2026-08-12T23:41:37.855505 (part 2)
Browse files- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/config.json +36 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/model.safetensors +3 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/optimizer.pt +3 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/rng_state.pth +3 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/scheduler.pt +3 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/tokenizer.json +0 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/tokenizer_config.json +13 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/trainer_state.json +925 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/training_args.bin +3 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/config.json +36 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/model.safetensors +3 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/tokenizer.json +0 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/tokenizer_config.json +13 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/training_args.bin +3 -0
- zain/Activation/out/glu-waleedglu_low-100L_run/training_log.jsonl +3 -0
- zain/Activation/wandb/debug-internal.log +45 -113
- zain/Activation/wandb/debug.log +19 -19
- zain/Activation/wandb/run-20260812_213354-drnrn7sc/logs/debug-core.log +7 -0
- zain/Activation/wandb/run-20260812_213440-m4b216ej/logs/debug-core.log +7 -0
- zain/Activation/wandb/run-20260812_213624-1sryr5l2/logs/debug-core.log +7 -0
- zain/Activation/wandb/run-20260812_220132-25l266uo/logs/debug-core.log +7 -0
- zain/Activation/wandb/run-20260812_222706-8exldg55/logs/debug-core.log +7 -0
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "waleedglu_low",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"TinyLlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"head_dim": 32,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 128,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 256,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"mlp_type": "glu",
|
| 19 |
+
"model_type": "tiny_llama",
|
| 20 |
+
"num_attention_heads": 4,
|
| 21 |
+
"num_hidden_layers": 100,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_parameters": {
|
| 27 |
+
"rope_theta": 10000.0,
|
| 28 |
+
"rope_type": "default"
|
| 29 |
+
},
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
|
| 32 |
+
"transformers_version": "5.16.0.dev0",
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"vocab_size": 4096,
|
| 35 |
+
"waleed_beta": 10.0
|
| 36 |
+
}
|
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73bbfda31a699a35d8ea0278b02b8a844a0471b1b992d6fb38ee67d63f4f9a19
|
| 3 |
+
size 33967272
|
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa4b8287958bee9c809c85f04d982c9a3fd7ed247ba81c374edf9dab2c5287c6
|
| 3 |
+
size 68504996
|
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
|
| 3 |
+
size 14244
|
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fae3f7a9f86d9663c06f6e22221bc9e6879cd9691e2b1bba04ee6412e2572f45
|
| 3 |
+
size 1064
|
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 1024,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,925 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.16852039096730703,
|
| 6 |
+
"eval_steps": 2498,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0013481631277384564,
|
| 14 |
+
"grad_norm": 2.125,
|
| 15 |
+
"learning_rate": 2.66e-05,
|
| 16 |
+
"loss": 8.299397277832032,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.002696326255476913,
|
| 21 |
+
"grad_norm": 1.3125,
|
| 22 |
+
"learning_rate": 5.46e-05,
|
| 23 |
+
"loss": 8.036466979980469,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.004044489383215369,
|
| 28 |
+
"grad_norm": 1.2734375,
|
| 29 |
+
"learning_rate": 8.259999999999999e-05,
|
| 30 |
+
"loss": 7.834572601318359,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.005392652510953826,
|
| 35 |
+
"grad_norm": 1.265625,
|
| 36 |
+
"learning_rate": 0.0001106,
|
| 37 |
+
"loss": 7.571878051757812,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.006740815638692282,
|
| 42 |
+
"grad_norm": 1.1953125,
|
| 43 |
+
"learning_rate": 0.0001386,
|
| 44 |
+
"loss": 7.237209320068359,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.008088978766430738,
|
| 49 |
+
"grad_norm": 1.15625,
|
| 50 |
+
"learning_rate": 0.00016659999999999998,
|
| 51 |
+
"loss": 6.865290832519531,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.009437141894169195,
|
| 56 |
+
"grad_norm": 0.9921875,
|
| 57 |
+
"learning_rate": 0.00019460000000000001,
|
| 58 |
+
"loss": 6.511030578613282,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.010785305021907651,
|
| 63 |
+
"grad_norm": 1.359375,
|
| 64 |
+
"learning_rate": 0.0002226,
|
| 65 |
+
"loss": 6.205308532714843,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.012133468149646108,
|
| 70 |
+
"grad_norm": 0.875,
|
| 71 |
+
"learning_rate": 0.00025059999999999997,
|
| 72 |
+
"loss": 5.942653656005859,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.013481631277384564,
|
| 77 |
+
"grad_norm": 0.7421875,
|
| 78 |
+
"learning_rate": 0.0002786,
|
| 79 |
+
"loss": 5.684436416625976,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.01482979440512302,
|
| 84 |
+
"grad_norm": 0.96484375,
|
| 85 |
+
"learning_rate": 0.00030659999999999997,
|
| 86 |
+
"loss": 5.42212028503418,
|
| 87 |
+
"step": 220
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.016177957532861477,
|
| 91 |
+
"grad_norm": 1.03125,
|
| 92 |
+
"learning_rate": 0.0003346,
|
| 93 |
+
"loss": 5.1382488250732425,
|
| 94 |
+
"step": 240
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.01752612066059993,
|
| 98 |
+
"grad_norm": 0.7578125,
|
| 99 |
+
"learning_rate": 0.00036260000000000003,
|
| 100 |
+
"loss": 4.889350891113281,
|
| 101 |
+
"step": 260
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.01887428378833839,
|
| 105 |
+
"grad_norm": 0.66015625,
|
| 106 |
+
"learning_rate": 0.0003906,
|
| 107 |
+
"loss": 4.6537117004394535,
|
| 108 |
+
"step": 280
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.020222446916076844,
|
| 112 |
+
"grad_norm": 0.78515625,
|
| 113 |
+
"learning_rate": 0.0004186,
|
| 114 |
+
"loss": 4.45124397277832,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.021570610043815303,
|
| 119 |
+
"grad_norm": 1.0390625,
|
| 120 |
+
"learning_rate": 0.0004466,
|
| 121 |
+
"loss": 4.264304733276367,
|
| 122 |
+
"step": 320
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.022918773171553757,
|
| 126 |
+
"grad_norm": 0.76171875,
|
| 127 |
+
"learning_rate": 0.00047460000000000004,
|
| 128 |
+
"loss": 4.108096313476563,
|
| 129 |
+
"step": 340
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.024266936299292215,
|
| 133 |
+
"grad_norm": 0.7734375,
|
| 134 |
+
"learning_rate": 0.0005026,
|
| 135 |
+
"loss": 3.9867103576660154,
|
| 136 |
+
"step": 360
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.02561509942703067,
|
| 140 |
+
"grad_norm": 0.86328125,
|
| 141 |
+
"learning_rate": 0.0005306,
|
| 142 |
+
"loss": 3.8636123657226564,
|
| 143 |
+
"step": 380
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.026963262554769128,
|
| 147 |
+
"grad_norm": 0.51953125,
|
| 148 |
+
"learning_rate": 0.0005586,
|
| 149 |
+
"loss": 3.7392677307128905,
|
| 150 |
+
"step": 400
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.028311425682507583,
|
| 154 |
+
"grad_norm": 0.5546875,
|
| 155 |
+
"learning_rate": 0.0005866,
|
| 156 |
+
"loss": 3.652521514892578,
|
| 157 |
+
"step": 420
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.02965958881024604,
|
| 161 |
+
"grad_norm": 0.52734375,
|
| 162 |
+
"learning_rate": 0.0006146,
|
| 163 |
+
"loss": 3.60003662109375,
|
| 164 |
+
"step": 440
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.031007751937984496,
|
| 168 |
+
"grad_norm": 0.515625,
|
| 169 |
+
"learning_rate": 0.0006426,
|
| 170 |
+
"loss": 3.5073707580566404,
|
| 171 |
+
"step": 460
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.032355915065722954,
|
| 175 |
+
"grad_norm": 0.62109375,
|
| 176 |
+
"learning_rate": 0.0006705999999999999,
|
| 177 |
+
"loss": 3.4376941680908204,
|
| 178 |
+
"step": 480
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.03370407819346141,
|
| 182 |
+
"grad_norm": 0.5546875,
|
| 183 |
+
"learning_rate": 0.0006986,
|
| 184 |
+
"loss": 3.366960144042969,
|
| 185 |
+
"step": 500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.03505224132119986,
|
| 189 |
+
"grad_norm": 0.515625,
|
| 190 |
+
"learning_rate": 0.0007,
|
| 191 |
+
"loss": 3.3081691741943358,
|
| 192 |
+
"step": 520
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.03640040444893832,
|
| 196 |
+
"grad_norm": 0.46484375,
|
| 197 |
+
"learning_rate": 0.0007,
|
| 198 |
+
"loss": 3.2408599853515625,
|
| 199 |
+
"step": 540
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.03774856757667678,
|
| 203 |
+
"grad_norm": 0.5703125,
|
| 204 |
+
"learning_rate": 0.0007,
|
| 205 |
+
"loss": 3.192046546936035,
|
| 206 |
+
"step": 560
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.03909673070441524,
|
| 210 |
+
"grad_norm": 0.455078125,
|
| 211 |
+
"learning_rate": 0.0007,
|
| 212 |
+
"loss": 3.1392486572265623,
|
| 213 |
+
"step": 580
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.04044489383215369,
|
| 217 |
+
"grad_norm": 0.484375,
|
| 218 |
+
"learning_rate": 0.0007,
|
| 219 |
+
"loss": 3.111465263366699,
|
| 220 |
+
"step": 600
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.04179305695989215,
|
| 224 |
+
"grad_norm": 0.455078125,
|
| 225 |
+
"learning_rate": 0.0007,
|
| 226 |
+
"loss": 3.0541475296020506,
|
| 227 |
+
"step": 620
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.043141220087630605,
|
| 231 |
+
"grad_norm": 0.482421875,
|
| 232 |
+
"learning_rate": 0.0007,
|
| 233 |
+
"loss": 3.0383369445800783,
|
| 234 |
+
"step": 640
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.044489383215369056,
|
| 238 |
+
"grad_norm": 0.470703125,
|
| 239 |
+
"learning_rate": 0.0007,
|
| 240 |
+
"loss": 2.9865617752075195,
|
| 241 |
+
"step": 660
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.045837546343107514,
|
| 245 |
+
"grad_norm": 0.478515625,
|
| 246 |
+
"learning_rate": 0.0007,
|
| 247 |
+
"loss": 2.9645502090454103,
|
| 248 |
+
"step": 680
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.04718570947084597,
|
| 252 |
+
"grad_norm": 0.46484375,
|
| 253 |
+
"learning_rate": 0.0007,
|
| 254 |
+
"loss": 2.923596000671387,
|
| 255 |
+
"step": 700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.04853387259858443,
|
| 259 |
+
"grad_norm": 0.412109375,
|
| 260 |
+
"learning_rate": 0.0007,
|
| 261 |
+
"loss": 2.8952192306518554,
|
| 262 |
+
"step": 720
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.04988203572632288,
|
| 266 |
+
"grad_norm": 0.4296875,
|
| 267 |
+
"learning_rate": 0.0007,
|
| 268 |
+
"loss": 2.860326385498047,
|
| 269 |
+
"step": 740
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.05123019885406134,
|
| 273 |
+
"grad_norm": 0.470703125,
|
| 274 |
+
"learning_rate": 0.0007,
|
| 275 |
+
"loss": 2.8456050872802736,
|
| 276 |
+
"step": 760
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.0525783619817998,
|
| 280 |
+
"grad_norm": 0.435546875,
|
| 281 |
+
"learning_rate": 0.0007,
|
| 282 |
+
"loss": 2.8421451568603517,
|
| 283 |
+
"step": 780
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.053926525109538256,
|
| 287 |
+
"grad_norm": 0.462890625,
|
| 288 |
+
"learning_rate": 0.0007,
|
| 289 |
+
"loss": 2.7993280410766603,
|
| 290 |
+
"step": 800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.05527468823727671,
|
| 294 |
+
"grad_norm": 0.45703125,
|
| 295 |
+
"learning_rate": 0.0007,
|
| 296 |
+
"loss": 2.7870391845703124,
|
| 297 |
+
"step": 820
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.056622851365015166,
|
| 301 |
+
"grad_norm": 0.470703125,
|
| 302 |
+
"learning_rate": 0.0007,
|
| 303 |
+
"loss": 2.7606174468994142,
|
| 304 |
+
"step": 840
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.057971014492753624,
|
| 308 |
+
"grad_norm": 0.439453125,
|
| 309 |
+
"learning_rate": 0.0007,
|
| 310 |
+
"loss": 2.719145584106445,
|
| 311 |
+
"step": 860
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.05931917762049208,
|
| 315 |
+
"grad_norm": 0.421875,
|
| 316 |
+
"learning_rate": 0.0007,
|
| 317 |
+
"loss": 2.6976993560791014,
|
| 318 |
+
"step": 880
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.06066734074823053,
|
| 322 |
+
"grad_norm": 0.458984375,
|
| 323 |
+
"learning_rate": 0.0007,
|
| 324 |
+
"loss": 2.684376907348633,
|
| 325 |
+
"step": 900
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.06201550387596899,
|
| 329 |
+
"grad_norm": 0.47265625,
|
| 330 |
+
"learning_rate": 0.0007,
|
| 331 |
+
"loss": 2.660353088378906,
|
| 332 |
+
"step": 920
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.06336366700370745,
|
| 336 |
+
"grad_norm": 0.42578125,
|
| 337 |
+
"learning_rate": 0.0007,
|
| 338 |
+
"loss": 2.647554397583008,
|
| 339 |
+
"step": 940
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.06471183013144591,
|
| 343 |
+
"grad_norm": 0.47265625,
|
| 344 |
+
"learning_rate": 0.0007,
|
| 345 |
+
"loss": 2.6243152618408203,
|
| 346 |
+
"step": 960
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.06605999325918437,
|
| 350 |
+
"grad_norm": 0.43359375,
|
| 351 |
+
"learning_rate": 0.0007,
|
| 352 |
+
"loss": 2.610305404663086,
|
| 353 |
+
"step": 980
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.06740815638692282,
|
| 357 |
+
"grad_norm": 0.455078125,
|
| 358 |
+
"learning_rate": 0.0007,
|
| 359 |
+
"loss": 2.6083221435546875,
|
| 360 |
+
"step": 1000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.06875631951466127,
|
| 364 |
+
"grad_norm": 0.4453125,
|
| 365 |
+
"learning_rate": 0.0007,
|
| 366 |
+
"loss": 2.5781414031982424,
|
| 367 |
+
"step": 1020
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.07010448264239973,
|
| 371 |
+
"grad_norm": 0.47265625,
|
| 372 |
+
"learning_rate": 0.0007,
|
| 373 |
+
"loss": 2.565291976928711,
|
| 374 |
+
"step": 1040
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.07145264577013818,
|
| 378 |
+
"grad_norm": 0.4453125,
|
| 379 |
+
"learning_rate": 0.0007,
|
| 380 |
+
"loss": 2.550668716430664,
|
| 381 |
+
"step": 1060
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.07280080889787664,
|
| 385 |
+
"grad_norm": 0.44921875,
|
| 386 |
+
"learning_rate": 0.0007,
|
| 387 |
+
"loss": 2.53463077545166,
|
| 388 |
+
"step": 1080
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0741489720256151,
|
| 392 |
+
"grad_norm": 0.416015625,
|
| 393 |
+
"learning_rate": 0.0007,
|
| 394 |
+
"loss": 2.5305706024169923,
|
| 395 |
+
"step": 1100
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.07549713515335356,
|
| 399 |
+
"grad_norm": 0.435546875,
|
| 400 |
+
"learning_rate": 0.0007,
|
| 401 |
+
"loss": 2.496831512451172,
|
| 402 |
+
"step": 1120
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.07684529828109202,
|
| 406 |
+
"grad_norm": 0.4453125,
|
| 407 |
+
"learning_rate": 0.0007,
|
| 408 |
+
"loss": 2.486662673950195,
|
| 409 |
+
"step": 1140
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.07819346140883048,
|
| 413 |
+
"grad_norm": 0.447265625,
|
| 414 |
+
"learning_rate": 0.0007,
|
| 415 |
+
"loss": 2.483187675476074,
|
| 416 |
+
"step": 1160
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.07954162453656892,
|
| 420 |
+
"grad_norm": 0.416015625,
|
| 421 |
+
"learning_rate": 0.0007,
|
| 422 |
+
"loss": 2.4800424575805664,
|
| 423 |
+
"step": 1180
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.08088978766430738,
|
| 427 |
+
"grad_norm": 0.453125,
|
| 428 |
+
"learning_rate": 0.0007,
|
| 429 |
+
"loss": 2.472176361083984,
|
| 430 |
+
"step": 1200
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.08223795079204584,
|
| 434 |
+
"grad_norm": 0.412109375,
|
| 435 |
+
"learning_rate": 0.0007,
|
| 436 |
+
"loss": 2.459552764892578,
|
| 437 |
+
"step": 1220
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.0835861139197843,
|
| 441 |
+
"grad_norm": 0.388671875,
|
| 442 |
+
"learning_rate": 0.0007,
|
| 443 |
+
"loss": 2.4468238830566404,
|
| 444 |
+
"step": 1240
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.08493427704752275,
|
| 448 |
+
"grad_norm": 0.44140625,
|
| 449 |
+
"learning_rate": 0.0007,
|
| 450 |
+
"loss": 2.4357337951660156,
|
| 451 |
+
"step": 1260
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.08628244017526121,
|
| 455 |
+
"grad_norm": 0.42578125,
|
| 456 |
+
"learning_rate": 0.0007,
|
| 457 |
+
"loss": 2.4172996520996093,
|
| 458 |
+
"step": 1280
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.08763060330299967,
|
| 462 |
+
"grad_norm": 0.44140625,
|
| 463 |
+
"learning_rate": 0.0007,
|
| 464 |
+
"loss": 2.41243953704834,
|
| 465 |
+
"step": 1300
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.08897876643073811,
|
| 469 |
+
"grad_norm": 0.40625,
|
| 470 |
+
"learning_rate": 0.0007,
|
| 471 |
+
"loss": 2.4029443740844725,
|
| 472 |
+
"step": 1320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.09032692955847657,
|
| 476 |
+
"grad_norm": 0.43359375,
|
| 477 |
+
"learning_rate": 0.0007,
|
| 478 |
+
"loss": 2.388625144958496,
|
| 479 |
+
"step": 1340
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.09167509268621503,
|
| 483 |
+
"grad_norm": 0.443359375,
|
| 484 |
+
"learning_rate": 0.0007,
|
| 485 |
+
"loss": 2.392447090148926,
|
| 486 |
+
"step": 1360
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.09302325581395349,
|
| 490 |
+
"grad_norm": 0.39453125,
|
| 491 |
+
"learning_rate": 0.0007,
|
| 492 |
+
"loss": 2.3689308166503906,
|
| 493 |
+
"step": 1380
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.09437141894169195,
|
| 497 |
+
"grad_norm": 0.400390625,
|
| 498 |
+
"learning_rate": 0.0007,
|
| 499 |
+
"loss": 2.362194061279297,
|
| 500 |
+
"step": 1400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.0957195820694304,
|
| 504 |
+
"grad_norm": 0.447265625,
|
| 505 |
+
"learning_rate": 0.0007,
|
| 506 |
+
"loss": 2.3735467910766603,
|
| 507 |
+
"step": 1420
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.09706774519716886,
|
| 511 |
+
"grad_norm": 0.408203125,
|
| 512 |
+
"learning_rate": 0.0007,
|
| 513 |
+
"loss": 2.3520509719848635,
|
| 514 |
+
"step": 1440
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.09841590832490732,
|
| 518 |
+
"grad_norm": 0.41796875,
|
| 519 |
+
"learning_rate": 0.0007,
|
| 520 |
+
"loss": 2.3391223907470704,
|
| 521 |
+
"step": 1460
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.09976407145264576,
|
| 525 |
+
"grad_norm": 0.392578125,
|
| 526 |
+
"learning_rate": 0.0007,
|
| 527 |
+
"loss": 2.32714729309082,
|
| 528 |
+
"step": 1480
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.10111223458038422,
|
| 532 |
+
"grad_norm": 0.40234375,
|
| 533 |
+
"learning_rate": 0.0007,
|
| 534 |
+
"loss": 2.314037322998047,
|
| 535 |
+
"step": 1500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.10246039770812268,
|
| 539 |
+
"grad_norm": 0.396484375,
|
| 540 |
+
"learning_rate": 0.0007,
|
| 541 |
+
"loss": 2.31822509765625,
|
| 542 |
+
"step": 1520
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.10380856083586114,
|
| 546 |
+
"grad_norm": 0.435546875,
|
| 547 |
+
"learning_rate": 0.0007,
|
| 548 |
+
"loss": 2.3066612243652345,
|
| 549 |
+
"step": 1540
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.1051567239635996,
|
| 553 |
+
"grad_norm": 0.396484375,
|
| 554 |
+
"learning_rate": 0.0007,
|
| 555 |
+
"loss": 2.297001266479492,
|
| 556 |
+
"step": 1560
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.10650488709133805,
|
| 560 |
+
"grad_norm": 0.396484375,
|
| 561 |
+
"learning_rate": 0.0007,
|
| 562 |
+
"loss": 2.3156213760375977,
|
| 563 |
+
"step": 1580
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.10785305021907651,
|
| 567 |
+
"grad_norm": 0.41015625,
|
| 568 |
+
"learning_rate": 0.0007,
|
| 569 |
+
"loss": 2.2851343154907227,
|
| 570 |
+
"step": 1600
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.10920121334681497,
|
| 574 |
+
"grad_norm": 0.404296875,
|
| 575 |
+
"learning_rate": 0.0007,
|
| 576 |
+
"loss": 2.285646438598633,
|
| 577 |
+
"step": 1620
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.11054937647455342,
|
| 581 |
+
"grad_norm": 0.41796875,
|
| 582 |
+
"learning_rate": 0.0007,
|
| 583 |
+
"loss": 2.297305870056152,
|
| 584 |
+
"step": 1640
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.11189753960229187,
|
| 588 |
+
"grad_norm": 0.37890625,
|
| 589 |
+
"learning_rate": 0.0007,
|
| 590 |
+
"loss": 2.280595397949219,
|
| 591 |
+
"step": 1660
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.11324570273003033,
|
| 595 |
+
"grad_norm": 0.392578125,
|
| 596 |
+
"learning_rate": 0.0007,
|
| 597 |
+
"loss": 2.26192626953125,
|
| 598 |
+
"step": 1680
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.11459386585776879,
|
| 602 |
+
"grad_norm": 0.3984375,
|
| 603 |
+
"learning_rate": 0.0007,
|
| 604 |
+
"loss": 2.2725173950195314,
|
| 605 |
+
"step": 1700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.11594202898550725,
|
| 609 |
+
"grad_norm": 0.41796875,
|
| 610 |
+
"learning_rate": 0.0007,
|
| 611 |
+
"loss": 2.2516456604003907,
|
| 612 |
+
"step": 1720
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.1172901921132457,
|
| 616 |
+
"grad_norm": 0.390625,
|
| 617 |
+
"learning_rate": 0.0007,
|
| 618 |
+
"loss": 2.240423583984375,
|
| 619 |
+
"step": 1740
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.11863835524098416,
|
| 623 |
+
"grad_norm": 0.423828125,
|
| 624 |
+
"learning_rate": 0.0007,
|
| 625 |
+
"loss": 2.2433708190917967,
|
| 626 |
+
"step": 1760
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.11998651836872262,
|
| 630 |
+
"grad_norm": 0.3984375,
|
| 631 |
+
"learning_rate": 0.0007,
|
| 632 |
+
"loss": 2.259623336791992,
|
| 633 |
+
"step": 1780
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.12133468149646107,
|
| 637 |
+
"grad_norm": 0.38671875,
|
| 638 |
+
"learning_rate": 0.0007,
|
| 639 |
+
"loss": 2.256252670288086,
|
| 640 |
+
"step": 1800
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.12268284462419952,
|
| 644 |
+
"grad_norm": 0.408203125,
|
| 645 |
+
"learning_rate": 0.0007,
|
| 646 |
+
"loss": 2.2460725784301756,
|
| 647 |
+
"step": 1820
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.12403100775193798,
|
| 651 |
+
"grad_norm": 0.4140625,
|
| 652 |
+
"learning_rate": 0.0007,
|
| 653 |
+
"loss": 2.215826225280762,
|
| 654 |
+
"step": 1840
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.12537917087967643,
|
| 658 |
+
"grad_norm": 0.37890625,
|
| 659 |
+
"learning_rate": 0.0007,
|
| 660 |
+
"loss": 2.2159719467163086,
|
| 661 |
+
"step": 1860
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.1267273340074149,
|
| 665 |
+
"grad_norm": 0.380859375,
|
| 666 |
+
"learning_rate": 0.0007,
|
| 667 |
+
"loss": 2.20712947845459,
|
| 668 |
+
"step": 1880
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.12807549713515334,
|
| 672 |
+
"grad_norm": 0.3828125,
|
| 673 |
+
"learning_rate": 0.0007,
|
| 674 |
+
"loss": 2.215154457092285,
|
| 675 |
+
"step": 1900
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.12942366026289182,
|
| 679 |
+
"grad_norm": 0.373046875,
|
| 680 |
+
"learning_rate": 0.0007,
|
| 681 |
+
"loss": 2.1930963516235353,
|
| 682 |
+
"step": 1920
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.13077182339063026,
|
| 686 |
+
"grad_norm": 0.423828125,
|
| 687 |
+
"learning_rate": 0.0007,
|
| 688 |
+
"loss": 2.2050329208374024,
|
| 689 |
+
"step": 1940
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.13211998651836873,
|
| 693 |
+
"grad_norm": 0.3984375,
|
| 694 |
+
"learning_rate": 0.0007,
|
| 695 |
+
"loss": 2.179214096069336,
|
| 696 |
+
"step": 1960
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.13346814964610718,
|
| 700 |
+
"grad_norm": 0.408203125,
|
| 701 |
+
"learning_rate": 0.0007,
|
| 702 |
+
"loss": 2.2014276504516603,
|
| 703 |
+
"step": 1980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.13481631277384565,
|
| 707 |
+
"grad_norm": 0.376953125,
|
| 708 |
+
"learning_rate": 0.0007,
|
| 709 |
+
"loss": 2.1765594482421875,
|
| 710 |
+
"step": 2000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.1361644759015841,
|
| 714 |
+
"grad_norm": 0.3828125,
|
| 715 |
+
"learning_rate": 0.0007,
|
| 716 |
+
"loss": 2.1848526000976562,
|
| 717 |
+
"step": 2020
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.13751263902932254,
|
| 721 |
+
"grad_norm": 0.42578125,
|
| 722 |
+
"learning_rate": 0.0007,
|
| 723 |
+
"loss": 2.16751651763916,
|
| 724 |
+
"step": 2040
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.138860802157061,
|
| 728 |
+
"grad_norm": 0.40234375,
|
| 729 |
+
"learning_rate": 0.0007,
|
| 730 |
+
"loss": 2.1859947204589845,
|
| 731 |
+
"step": 2060
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.14020896528479945,
|
| 735 |
+
"grad_norm": 0.3984375,
|
| 736 |
+
"learning_rate": 0.0007,
|
| 737 |
+
"loss": 2.1614406585693358,
|
| 738 |
+
"step": 2080
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.14155712841253792,
|
| 742 |
+
"grad_norm": 0.376953125,
|
| 743 |
+
"learning_rate": 0.0007,
|
| 744 |
+
"loss": 2.1523923873901367,
|
| 745 |
+
"step": 2100
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.14290529154027637,
|
| 749 |
+
"grad_norm": 0.38671875,
|
| 750 |
+
"learning_rate": 0.0007,
|
| 751 |
+
"loss": 2.1621030807495116,
|
| 752 |
+
"step": 2120
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.14425345466801484,
|
| 756 |
+
"grad_norm": 0.390625,
|
| 757 |
+
"learning_rate": 0.0007,
|
| 758 |
+
"loss": 2.165338897705078,
|
| 759 |
+
"step": 2140
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.14560161779575329,
|
| 763 |
+
"grad_norm": 0.369140625,
|
| 764 |
+
"learning_rate": 0.0007,
|
| 765 |
+
"loss": 2.14947566986084,
|
| 766 |
+
"step": 2160
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.14694978092349173,
|
| 770 |
+
"grad_norm": 0.388671875,
|
| 771 |
+
"learning_rate": 0.0007,
|
| 772 |
+
"loss": 2.1582948684692385,
|
| 773 |
+
"step": 2180
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.1482979440512302,
|
| 777 |
+
"grad_norm": 0.369140625,
|
| 778 |
+
"learning_rate": 0.0007,
|
| 779 |
+
"loss": 2.1333045959472656,
|
| 780 |
+
"step": 2200
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.14964610717896865,
|
| 784 |
+
"grad_norm": 0.388671875,
|
| 785 |
+
"learning_rate": 0.0007,
|
| 786 |
+
"loss": 2.1407724380493165,
|
| 787 |
+
"step": 2220
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.15099427030670712,
|
| 791 |
+
"grad_norm": 0.3828125,
|
| 792 |
+
"learning_rate": 0.0007,
|
| 793 |
+
"loss": 2.149934196472168,
|
| 794 |
+
"step": 2240
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.15234243343444556,
|
| 798 |
+
"grad_norm": 0.41015625,
|
| 799 |
+
"learning_rate": 0.0007,
|
| 800 |
+
"loss": 2.1294736862182617,
|
| 801 |
+
"step": 2260
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.15369059656218403,
|
| 805 |
+
"grad_norm": 0.376953125,
|
| 806 |
+
"learning_rate": 0.0007,
|
| 807 |
+
"loss": 2.140834617614746,
|
| 808 |
+
"step": 2280
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.15503875968992248,
|
| 812 |
+
"grad_norm": 0.361328125,
|
| 813 |
+
"learning_rate": 0.0007,
|
| 814 |
+
"loss": 2.1200790405273438,
|
| 815 |
+
"step": 2300
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.15638692281766095,
|
| 819 |
+
"grad_norm": 0.3984375,
|
| 820 |
+
"learning_rate": 0.0007,
|
| 821 |
+
"loss": 2.1302547454833984,
|
| 822 |
+
"step": 2320
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.1577350859453994,
|
| 826 |
+
"grad_norm": 0.37109375,
|
| 827 |
+
"learning_rate": 0.0007,
|
| 828 |
+
"loss": 2.121130180358887,
|
| 829 |
+
"step": 2340
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.15908324907313784,
|
| 833 |
+
"grad_norm": 0.375,
|
| 834 |
+
"learning_rate": 0.0007,
|
| 835 |
+
"loss": 2.123651123046875,
|
| 836 |
+
"step": 2360
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.1604314122008763,
|
| 840 |
+
"grad_norm": 0.376953125,
|
| 841 |
+
"learning_rate": 0.0007,
|
| 842 |
+
"loss": 2.126963806152344,
|
| 843 |
+
"step": 2380
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.16177957532861476,
|
| 847 |
+
"grad_norm": 0.376953125,
|
| 848 |
+
"learning_rate": 0.0007,
|
| 849 |
+
"loss": 2.108779525756836,
|
| 850 |
+
"step": 2400
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.16312773845635323,
|
| 854 |
+
"grad_norm": 0.39453125,
|
| 855 |
+
"learning_rate": 0.0007,
|
| 856 |
+
"loss": 2.1131147384643554,
|
| 857 |
+
"step": 2420
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.16447590158409167,
|
| 861 |
+
"grad_norm": 0.388671875,
|
| 862 |
+
"learning_rate": 0.0007,
|
| 863 |
+
"loss": 2.099979591369629,
|
| 864 |
+
"step": 2440
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.16582406471183014,
|
| 868 |
+
"grad_norm": 0.390625,
|
| 869 |
+
"learning_rate": 0.0007,
|
| 870 |
+
"loss": 2.113809013366699,
|
| 871 |
+
"step": 2460
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.1671722278395686,
|
| 875 |
+
"grad_norm": 0.384765625,
|
| 876 |
+
"learning_rate": 0.0007,
|
| 877 |
+
"loss": 2.1132349014282226,
|
| 878 |
+
"step": 2480
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.1683855746545332,
|
| 882 |
+
"eval_loss": 2.108184814453125,
|
| 883 |
+
"eval_runtime": 16.256,
|
| 884 |
+
"eval_samples_per_second": 586.062,
|
| 885 |
+
"eval_steps_per_second": 0.615,
|
| 886 |
+
"step": 2498
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.16852039096730703,
|
| 890 |
+
"grad_norm": 0.359375,
|
| 891 |
+
"learning_rate": 0.0007,
|
| 892 |
+
"loss": 2.0956993103027344,
|
| 893 |
+
"step": 2500
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.16852039096730703,
|
| 897 |
+
"eval_loss": 2.106821060180664,
|
| 898 |
+
"eval_runtime": 16.2449,
|
| 899 |
+
"eval_samples_per_second": 586.463,
|
| 900 |
+
"eval_steps_per_second": 0.616,
|
| 901 |
+
"step": 2500
|
| 902 |
+
}
|
| 903 |
+
],
|
| 904 |
+
"logging_steps": 20,
|
| 905 |
+
"max_steps": 2500,
|
| 906 |
+
"num_input_tokens_seen": 0,
|
| 907 |
+
"num_train_epochs": 1,
|
| 908 |
+
"save_steps": 100,
|
| 909 |
+
"stateful_callbacks": {
|
| 910 |
+
"TrainerControl": {
|
| 911 |
+
"args": {
|
| 912 |
+
"should_epoch_stop": false,
|
| 913 |
+
"should_evaluate": false,
|
| 914 |
+
"should_log": false,
|
| 915 |
+
"should_save": true,
|
| 916 |
+
"should_training_stop": true
|
| 917 |
+
},
|
| 918 |
+
"attributes": {}
|
| 919 |
+
}
|
| 920 |
+
},
|
| 921 |
+
"total_flos": 8065709506560000.0,
|
| 922 |
+
"train_batch_size": 64,
|
| 923 |
+
"trial_name": null,
|
| 924 |
+
"trial_params": null
|
| 925 |
+
}
|
zain/Activation/out/glu-waleedglu_low-100L_run/checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3381278f5755fc3f2519824864b1ad9e5cc81a11ca4bc0fc3bdf02cc524b903e
|
| 3 |
+
size 4920
|
zain/Activation/out/glu-waleedglu_low-100L_run/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "waleedglu_low",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"TinyLlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"head_dim": 32,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 128,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 256,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"mlp_type": "glu",
|
| 19 |
+
"model_type": "tiny_llama",
|
| 20 |
+
"num_attention_heads": 4,
|
| 21 |
+
"num_hidden_layers": 100,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_parameters": {
|
| 27 |
+
"rope_theta": 10000.0,
|
| 28 |
+
"rope_type": "default"
|
| 29 |
+
},
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
|
| 32 |
+
"transformers_version": "5.16.0.dev0",
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"vocab_size": 4096,
|
| 35 |
+
"waleed_beta": 10.0
|
| 36 |
+
}
|
zain/Activation/out/glu-waleedglu_low-100L_run/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73bbfda31a699a35d8ea0278b02b8a844a0471b1b992d6fb38ee67d63f4f9a19
|
| 3 |
+
size 33967272
|
zain/Activation/out/glu-waleedglu_low-100L_run/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
zain/Activation/out/glu-waleedglu_low-100L_run/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 1024,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|
zain/Activation/out/glu-waleedglu_low-100L_run/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3381278f5755fc3f2519824864b1ad9e5cc81a11ca4bc0fc3bdf02cc524b903e
|
| 3 |
+
size 4920
|
zain/Activation/out/glu-waleedglu_low-100L_run/training_log.jsonl
CHANGED
|
@@ -124,3 +124,6 @@
|
|
| 124 |
{"step": 2480, "epoch": 0.1671722278395686, "timestamp": 1786577767.633616, "loss": 2.1132349014282226, "grad_norm": 0.384765625, "learning_rate": 0.0007, "train/total_time_seconds": 628.9794939644635, "train/time_per_step_avg": 0.2529666190221906, "train/epoch_time_elapsed": 760.3851487226784, "train/estimated_remaining_minutes": 0.08454025456511607}
|
| 125 |
{"step": 2498, "epoch": 0.1683855746545332, "timestamp": 1786577789.3266292, "eval_loss": 2.108184814453125, "eval_runtime": 16.256, "eval_samples_per_second": 586.062, "eval_steps_per_second": 0.615, "train/total_time_seconds": 633.5167688988149, "train/time_per_step_avg": 0.25226373694837095, "train/epoch_time_elapsed": 782.0781616792083, "train/estimated_remaining_minutes": 0.008453653174523817}
|
| 126 |
{"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1786577789.929582, "loss": 2.0956993103027344, "grad_norm": 0.359375, "learning_rate": 0.0007, "train/total_time_seconds": 634.0191961415112, "train/time_per_step_avg": 0.25226678982377054, "train/epoch_time_elapsed": 782.6811165064573, "train/estimated_remaining_minutes": 0.0}
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
{"step": 2480, "epoch": 0.1671722278395686, "timestamp": 1786577767.633616, "loss": 2.1132349014282226, "grad_norm": 0.384765625, "learning_rate": 0.0007, "train/total_time_seconds": 628.9794939644635, "train/time_per_step_avg": 0.2529666190221906, "train/epoch_time_elapsed": 760.3851487226784, "train/estimated_remaining_minutes": 0.08454025456511607}
|
| 125 |
{"step": 2498, "epoch": 0.1683855746545332, "timestamp": 1786577789.3266292, "eval_loss": 2.108184814453125, "eval_runtime": 16.256, "eval_samples_per_second": 586.062, "eval_steps_per_second": 0.615, "train/total_time_seconds": 633.5167688988149, "train/time_per_step_avg": 0.25226373694837095, "train/epoch_time_elapsed": 782.0781616792083, "train/estimated_remaining_minutes": 0.008453653174523817}
|
| 126 |
{"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1786577789.929582, "loss": 2.0956993103027344, "grad_norm": 0.359375, "learning_rate": 0.0007, "train/total_time_seconds": 634.0191961415112, "train/time_per_step_avg": 0.25226678982377054, "train/epoch_time_elapsed": 782.6811165064573, "train/estimated_remaining_minutes": 0.0}
|
| 127 |
+
{"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1786577806.1759975, "eval_loss": 2.106821060180664, "eval_runtime": 16.2449, "eval_samples_per_second": 586.463, "eval_steps_per_second": 0.616, "train/total_time_seconds": 634.0191961415112, "train/time_per_step_avg": 0.25226678982377054, "train/epoch_time_elapsed": 798.9275299459696, "train/estimated_remaining_minutes": 0.0}
|
| 128 |
+
{"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1786577806.465999, "train_runtime": 800.0191, "train_samples_per_second": 199.995, "train_steps_per_second": 3.125, "total_flos": 8065709506560000.0, "train_loss": 2.999342321777344, "train/total_time_seconds": 634.0191961415112, "train/time_per_step_avg": 0.25226678982377054, "train/epoch_time_elapsed": 799.2175308428705, "train/estimated_remaining_minutes": 0.0}
|
| 129 |
+
{"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1786577822.6914845, "eval_loss": 2.106821060180664, "eval_runtime": 16.2219, "eval_samples_per_second": 587.293, "eval_steps_per_second": 0.616, "train/total_time_seconds": 634.0191961415112, "train/time_per_step_avg": 0.25226678982377054, "train/epoch_time_elapsed": 815.4430170059204, "train/estimated_remaining_minutes": 0.0}
|
zain/Activation/wandb/debug-internal.log
CHANGED
|
@@ -1,113 +1,45 @@
|
|
| 1 |
-
{"time":"2026-08-12T23:
|
| 2 |
-
{"time":"2026-08-12T23:
|
| 3 |
-
{"time":"2026-08-12T23:
|
| 4 |
-
{"time":"2026-08-12T23:
|
| 5 |
-
{"time":"2026-08-12T23:
|
| 6 |
-
{"time":"2026-08-12T23:
|
| 7 |
-
{"time":"2026-08-12T23:
|
| 8 |
-
{"time":"2026-08-12T23:
|
| 9 |
-
{"time":"2026-08-12T23:
|
| 10 |
-
{"time":"2026-08-12T23:
|
| 11 |
-
{"time":"2026-08-12T23:
|
| 12 |
-
{"time":"2026-08-12T23:
|
| 13 |
-
{"time":"2026-08-12T23:
|
| 14 |
-
{"time":"2026-08-12T23:
|
| 15 |
-
{"time":"2026-08-12T23:
|
| 16 |
-
{"time":"2026-08-12T23:
|
| 17 |
-
{"time":"2026-08-12T23:
|
| 18 |
-
{"time":"2026-08-12T23:
|
| 19 |
-
{"time":"2026-08-12T23:
|
| 20 |
-
{"time":"2026-08-12T23:
|
| 21 |
-
{"time":"2026-08-12T23:
|
| 22 |
-
{"time":"2026-08-12T23:
|
| 23 |
-
{"time":"2026-08-12T23:
|
| 24 |
-
{"time":"2026-08-12T23:
|
| 25 |
-
{"time":"2026-08-12T23:
|
| 26 |
-
{"time":"2026-08-12T23:
|
| 27 |
-
{"time":"2026-08-12T23:
|
| 28 |
-
{"time":"2026-08-12T23:
|
| 29 |
-
{"time":"2026-08-12T23:
|
| 30 |
-
{"time":"2026-08-12T23:
|
| 31 |
-
{"time":"2026-08-12T23:
|
| 32 |
-
{"time":"2026-08-12T23:
|
| 33 |
-
{"time":"2026-08-12T23:
|
| 34 |
-
{"time":"2026-08-12T23:
|
| 35 |
-
{"time":"2026-08-12T23:
|
| 36 |
-
{"time":"2026-08-12T23:
|
| 37 |
-
{"time":"2026-08-12T23:
|
| 38 |
-
{"time":"2026-08-12T23:
|
| 39 |
-
{"time":"2026-08-12T23:
|
| 40 |
-
{"time":"2026-08-12T23:
|
| 41 |
-
{"time":"2026-08-12T23:
|
| 42 |
-
{"time":"2026-08-12T23:
|
| 43 |
-
{"time":"2026-08-12T23:
|
| 44 |
-
{"time":"2026-08-12T23:
|
| 45 |
-
{"time":"2026-08-12T23:
|
| 46 |
-
{"time":"2026-08-12T23:28:12.834102013Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":2,"events_offset":36,"events_lines":2,"console_offset":80,"console_lines":1}
|
| 47 |
-
{"time":"2026-08-12T23:28:12.971550206Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 48 |
-
{"time":"2026-08-12T23:28:27.834342008Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":46,"history_lines":3,"events_offset":38,"events_lines":2,"console_offset":85,"console_lines":10}
|
| 49 |
-
{"time":"2026-08-12T23:28:27.965690965Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 50 |
-
{"time":"2026-08-12T23:28:42.834578141Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":49,"history_lines":2,"events_offset":40,"events_lines":2,"console_offset":90,"console_lines":1}
|
| 51 |
-
{"time":"2026-08-12T23:28:42.969304267Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 52 |
-
{"time":"2026-08-12T23:28:57.835185189Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":51,"history_lines":2,"events_offset":42,"events_lines":2,"console_offset":95,"console_lines":9}
|
| 53 |
-
{"time":"2026-08-12T23:28:57.981926619Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 54 |
-
{"time":"2026-08-12T23:29:12.834349936Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":53,"history_lines":3,"events_offset":44,"events_lines":2,"console_offset":100,"console_lines":1}
|
| 55 |
-
{"time":"2026-08-12T23:29:12.942635971Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 56 |
-
{"time":"2026-08-12T23:29:27.834543175Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":56,"history_lines":2,"events_offset":46,"events_lines":2,"console_offset":104,"console_lines":10}
|
| 57 |
-
{"time":"2026-08-12T23:29:27.951955851Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 58 |
-
{"time":"2026-08-12T23:29:42.834508359Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":58,"history_lines":3,"events_offset":48,"events_lines":2,"console_offset":110,"console_lines":1}
|
| 59 |
-
{"time":"2026-08-12T23:29:43.024842238Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 60 |
-
{"time":"2026-08-12T23:29:57.834038553Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":61,"history_lines":2,"events_offset":50,"events_lines":2,"console_offset":114,"console_lines":10}
|
| 61 |
-
{"time":"2026-08-12T23:29:57.993106225Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 62 |
-
{"time":"2026-08-12T23:30:12.834078313Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":63,"history_lines":3,"events_offset":52,"events_lines":2,"console_offset":120,"console_lines":1}
|
| 63 |
-
{"time":"2026-08-12T23:30:12.974229198Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 64 |
-
{"time":"2026-08-12T23:30:27.834158455Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":66,"history_lines":2,"events_offset":54,"events_lines":2,"console_offset":124,"console_lines":10}
|
| 65 |
-
{"time":"2026-08-12T23:30:27.964363306Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 66 |
-
{"time":"2026-08-12T23:30:42.83460144Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":68,"history_lines":3,"events_offset":56,"events_lines":2,"console_offset":130,"console_lines":1}
|
| 67 |
-
{"time":"2026-08-12T23:30:42.961635661Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 68 |
-
{"time":"2026-08-12T23:30:57.834059991Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":71,"history_lines":2,"events_offset":58,"events_lines":2,"console_offset":134,"console_lines":10}
|
| 69 |
-
{"time":"2026-08-12T23:30:57.993131825Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 70 |
-
{"time":"2026-08-12T23:31:12.834436696Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":73,"history_lines":2,"events_offset":60,"events_lines":2,"console_offset":140,"console_lines":1}
|
| 71 |
-
{"time":"2026-08-12T23:31:13.009450597Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 72 |
-
{"time":"2026-08-12T23:31:27.83439083Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":75,"history_lines":3,"events_offset":62,"events_lines":2,"console_offset":144,"console_lines":10}
|
| 73 |
-
{"time":"2026-08-12T23:31:27.987733053Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 74 |
-
{"time":"2026-08-12T23:31:42.833841489Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":78,"history_lines":2,"events_offset":64,"events_lines":2,"console_offset":150,"console_lines":1}
|
| 75 |
-
{"time":"2026-08-12T23:31:42.943366283Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 76 |
-
{"time":"2026-08-12T23:31:57.834350975Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":80,"history_lines":3,"events_offset":66,"events_lines":2,"console_offset":154,"console_lines":10}
|
| 77 |
-
{"time":"2026-08-12T23:31:57.967204982Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 78 |
-
{"time":"2026-08-12T23:32:12.8345927Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":83,"history_lines":2,"events_offset":68,"events_lines":2,"console_offset":160,"console_lines":1}
|
| 79 |
-
{"time":"2026-08-12T23:32:13.025938975Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 80 |
-
{"time":"2026-08-12T23:32:27.834764312Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":85,"history_lines":3,"events_offset":70,"events_lines":2,"console_offset":164,"console_lines":10}
|
| 81 |
-
{"time":"2026-08-12T23:32:27.995242979Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 82 |
-
{"time":"2026-08-12T23:32:42.834472459Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":88,"history_lines":2,"events_offset":72,"events_lines":2,"console_offset":170,"console_lines":1}
|
| 83 |
-
{"time":"2026-08-12T23:32:43.025069599Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 84 |
-
{"time":"2026-08-12T23:32:57.833985285Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":90,"history_lines":3,"events_offset":74,"events_lines":2,"console_offset":174,"console_lines":10}
|
| 85 |
-
{"time":"2026-08-12T23:32:57.953201068Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 86 |
-
{"time":"2026-08-12T23:33:12.834438847Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":93,"history_lines":2,"events_offset":76,"events_lines":2,"console_offset":180,"console_lines":1}
|
| 87 |
-
{"time":"2026-08-12T23:33:12.98519215Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 88 |
-
{"time":"2026-08-12T23:33:27.833989897Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":95,"history_lines":2,"events_offset":78,"events_lines":2,"console_offset":184,"console_lines":9}
|
| 89 |
-
{"time":"2026-08-12T23:33:27.997860879Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 90 |
-
{"time":"2026-08-12T23:33:42.834060785Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":97,"history_lines":3,"events_offset":80,"events_lines":2,"console_offset":190,"console_lines":1}
|
| 91 |
-
{"time":"2026-08-12T23:33:42.973471839Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 92 |
-
{"time":"2026-08-12T23:33:57.834205919Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":100,"history_lines":2,"events_offset":82,"events_lines":2,"console_offset":193,"console_lines":10}
|
| 93 |
-
{"time":"2026-08-12T23:33:57.998324717Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 94 |
-
{"time":"2026-08-12T23:34:12.833795161Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":102,"history_lines":3,"events_offset":84,"events_lines":2,"console_offset":200,"console_lines":1}
|
| 95 |
-
{"time":"2026-08-12T23:34:13.010483711Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 96 |
-
{"time":"2026-08-12T23:34:27.834077162Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":105,"history_lines":2,"events_offset":86,"events_lines":2,"console_offset":203,"console_lines":10}
|
| 97 |
-
{"time":"2026-08-12T23:34:27.970181788Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 98 |
-
{"time":"2026-08-12T23:34:42.834043984Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":107,"history_lines":3,"events_offset":88,"events_lines":2,"console_offset":210,"console_lines":1}
|
| 99 |
-
{"time":"2026-08-12T23:34:43.010800637Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 100 |
-
{"time":"2026-08-12T23:34:57.83479331Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":110,"history_lines":2,"events_offset":90,"events_lines":2,"console_offset":213,"console_lines":10}
|
| 101 |
-
{"time":"2026-08-12T23:34:57.978566326Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 102 |
-
{"time":"2026-08-12T23:35:12.834369042Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":112,"history_lines":3,"events_offset":92,"events_lines":2,"console_offset":220,"console_lines":1}
|
| 103 |
-
{"time":"2026-08-12T23:35:12.966977471Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 104 |
-
{"time":"2026-08-12T23:35:27.833877403Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":115,"history_lines":2,"events_offset":94,"events_lines":2,"console_offset":223,"console_lines":10}
|
| 105 |
-
{"time":"2026-08-12T23:35:27.987087367Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 106 |
-
{"time":"2026-08-12T23:35:42.834008573Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":117,"history_lines":2,"events_offset":96,"events_lines":2,"console_offset":230,"console_lines":1}
|
| 107 |
-
{"time":"2026-08-12T23:35:42.989206129Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 108 |
-
{"time":"2026-08-12T23:35:57.834262627Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":119,"history_lines":3,"events_offset":98,"events_lines":2,"console_offset":230,"console_lines":1}
|
| 109 |
-
{"time":"2026-08-12T23:35:57.981066922Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 110 |
-
{"time":"2026-08-12T23:36:12.834049324Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":122,"history_lines":2,"events_offset":100,"events_lines":2,"console_offset":233,"console_lines":12}
|
| 111 |
-
{"time":"2026-08-12T23:36:13.032234814Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 112 |
-
{"time":"2026-08-12T23:36:27.833821632Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":102,"events_lines":2,"console_offset":240,"console_lines":1}
|
| 113 |
-
{"time":"2026-08-12T23:36:28.003341226Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
|
|
|
| 1 |
+
{"time":"2026-08-12T23:37:04.659535647Z","level":"INFO","msg":"wandb-core"}
|
| 2 |
+
{"time":"2026-08-12T23:37:04.659713088Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
|
| 3 |
+
{"time":"2026-08-12T23:37:04.922724672Z","level":"INFO","msg":"stream: created new stream","id":"tpo5j00e"}
|
| 4 |
+
{"time":"2026-08-12T23:37:04.922802037Z","level":"INFO","msg":"handler: started"}
|
| 5 |
+
{"time":"2026-08-12T23:37:04.922869688Z","level":"INFO","msg":"stream: started"}
|
| 6 |
+
{"time":"2026-08-12T23:37:04.92287935Z","level":"INFO","msg":"writer: started","stream_id":"tpo5j00e"}
|
| 7 |
+
{"time":"2026-08-12T23:37:04.922905677Z","level":"INFO","msg":"sender: started"}
|
| 8 |
+
{"time":"2026-08-12T23:37:05.873245481Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
|
| 9 |
+
{"time":"2026-08-12T23:37:05.976836036Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 10 |
+
{"time":"2026-08-12T23:37:20.873549402Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":3,"uploaded_len":2}
|
| 11 |
+
{"time":"2026-08-12T23:37:21.046938976Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 12 |
+
{"time":"2026-08-12T23:37:35.873403247Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":3,"events_offset":2,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 13 |
+
{"time":"2026-08-12T23:37:35.987842224Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 14 |
+
{"time":"2026-08-12T23:37:50.873628839Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":2,"events_offset":4,"events_lines":2,"console_offset":3,"console_lines":10}
|
| 15 |
+
{"time":"2026-08-12T23:37:51.002271058Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 16 |
+
{"time":"2026-08-12T23:38:05.873482676Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":3,"events_offset":6,"events_lines":2,"console_offset":10,"console_lines":1}
|
| 17 |
+
{"time":"2026-08-12T23:38:06.053532244Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 18 |
+
{"time":"2026-08-12T23:38:20.874242569Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":10,"history_lines":3,"events_offset":8,"events_lines":2,"console_offset":13,"console_lines":11}
|
| 19 |
+
{"time":"2026-08-12T23:38:21.011343881Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 20 |
+
{"time":"2026-08-12T23:38:35.873927769Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":13,"history_lines":2,"events_offset":10,"events_lines":2,"console_offset":20,"console_lines":1}
|
| 21 |
+
{"time":"2026-08-12T23:38:36.001089695Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 22 |
+
{"time":"2026-08-12T23:38:50.87405577Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":15,"history_lines":3,"events_offset":12,"events_lines":2,"console_offset":24,"console_lines":10}
|
| 23 |
+
{"time":"2026-08-12T23:38:51.005082427Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 24 |
+
{"time":"2026-08-12T23:39:05.874376666Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":18,"history_lines":2,"events_offset":14,"events_lines":2,"console_offset":30,"console_lines":1}
|
| 25 |
+
{"time":"2026-08-12T23:39:06.017367832Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 26 |
+
{"time":"2026-08-12T23:39:20.874387696Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":20,"history_lines":3,"events_offset":16,"events_lines":2,"console_offset":34,"console_lines":10}
|
| 27 |
+
{"time":"2026-08-12T23:39:21.01825087Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 28 |
+
{"time":"2026-08-12T23:39:35.873696527Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":23,"history_lines":3,"events_offset":18,"events_lines":2,"console_offset":40,"console_lines":1}
|
| 29 |
+
{"time":"2026-08-12T23:39:36.03804034Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 30 |
+
{"time":"2026-08-12T23:39:50.874252929Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":26,"history_lines":2,"events_offset":20,"events_lines":2,"console_offset":44,"console_lines":10}
|
| 31 |
+
{"time":"2026-08-12T23:39:51.062458509Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 32 |
+
{"time":"2026-08-12T23:40:05.874313285Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":28,"history_lines":3,"events_offset":22,"events_lines":2,"console_offset":50,"console_lines":1}
|
| 33 |
+
{"time":"2026-08-12T23:40:06.080511399Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 34 |
+
{"time":"2026-08-12T23:40:20.873571774Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":31,"history_lines":3,"events_offset":24,"events_lines":2,"console_offset":54,"console_lines":11}
|
| 35 |
+
{"time":"2026-08-12T23:40:20.98995242Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 36 |
+
{"time":"2026-08-12T23:40:35.873978401Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":34,"history_lines":2,"events_offset":26,"events_lines":2,"console_offset":60,"console_lines":1}
|
| 37 |
+
{"time":"2026-08-12T23:40:36.01278686Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 38 |
+
{"time":"2026-08-12T23:40:50.874152142Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":36,"history_lines":3,"events_offset":28,"events_lines":2,"console_offset":65,"console_lines":10}
|
| 39 |
+
{"time":"2026-08-12T23:40:51.035169968Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 40 |
+
{"time":"2026-08-12T23:41:05.874071812Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":39,"history_lines":2,"events_offset":30,"events_lines":2,"console_offset":70,"console_lines":1}
|
| 41 |
+
{"time":"2026-08-12T23:41:06.28590686Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 42 |
+
{"time":"2026-08-12T23:41:20.873943526Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":41,"history_lines":3,"events_offset":32,"events_lines":2,"console_offset":75,"console_lines":10}
|
| 43 |
+
{"time":"2026-08-12T23:41:21.027108603Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 44 |
+
{"time":"2026-08-12T23:41:35.873830974Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":3,"events_offset":34,"events_lines":2,"console_offset":80,"console_lines":1}
|
| 45 |
+
{"time":"2026-08-12T23:41:36.078356676Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
zain/Activation/wandb/debug.log
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
-
2026-08-12 23:
|
| 2 |
-
2026-08-12 23:
|
| 3 |
-
2026-08-12 23:
|
| 4 |
-
2026-08-12 23:
|
| 5 |
config: {'_wandb': {}}
|
| 6 |
-
2026-08-12 23:
|
| 7 |
-
2026-08-12 23:
|
| 8 |
-
2026-08-12 23:
|
| 9 |
-
2026-08-12 23:
|
| 10 |
-
2026-08-12 23:
|
| 11 |
-
2026-08-12 23:
|
| 12 |
-
2026-08-12 23:
|
| 13 |
-
2026-08-12 23:
|
| 14 |
-
2026-08-12 23:
|
| 15 |
-
2026-08-12 23:
|
| 16 |
-
2026-08-12 23:
|
| 17 |
-
2026-08-12 23:
|
| 18 |
-
2026-08-12 23:
|
| 19 |
-
2026-08-12 23:
|
| 20 |
-
2026-08-12 23:
|
|
|
|
| 1 |
+
2026-08-12 23:37:04,658 INFO MainThread:3978000 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_233704-tpo5j00e/logs/debug.log
|
| 2 |
+
2026-08-12 23:37:04,658 INFO MainThread:3978000 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_233704-tpo5j00e/logs/debug-internal.log
|
| 3 |
+
2026-08-12 23:37:04,658 INFO MainThread:3978000 [wandb_init.py:init():772] calling init triggers
|
| 4 |
+
2026-08-12 23:37:04,658 INFO MainThread:3978000 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
|
| 5 |
config: {'_wandb': {}}
|
| 6 |
+
2026-08-12 23:37:04,658 INFO MainThread:3978000 [wandb_init.py:init():820] starting backend
|
| 7 |
+
2026-08-12 23:37:04,658 INFO MainThread:3978000 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
|
| 8 |
+
2026-08-12 23:37:04,658 INFO MainThread:3978000 [wandb_init.py:init():835] sending inform_init request
|
| 9 |
+
2026-08-12 23:37:04,923 INFO MainThread:3978000 [wandb_init.py:init():840] backend started and connected
|
| 10 |
+
2026-08-12 23:37:04,924 INFO MainThread:3978000 [wandb_init.py:init():910] updated telemetry
|
| 11 |
+
2026-08-12 23:37:04,931 INFO MainThread:3978000 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
|
| 12 |
+
2026-08-12 23:37:05,231 INFO MainThread:3978000 [wandb_init.py:init():978] starting run threads in backend
|
| 13 |
+
2026-08-12 23:37:05,308 INFO MainThread:3978000 [wandb_run.py:_console_start():2621] atexit reg
|
| 14 |
+
2026-08-12 23:37:05,309 INFO MainThread:3978000 [wandb_run.py:_redirect():2471] redirect: wrap_raw
|
| 15 |
+
2026-08-12 23:37:05,309 INFO MainThread:3978000 [wandb_run.py:_redirect():2540] Wrapping output streams.
|
| 16 |
+
2026-08-12 23:37:05,309 INFO MainThread:3978000 [wandb_run.py:_redirect():2563] Redirects installed.
|
| 17 |
+
2026-08-12 23:37:05,309 INFO MainThread:3978000 [wandb_init.py:init():1016] run started, returning control to user process
|
| 18 |
+
2026-08-12 23:37:05,310 INFO MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 100, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'linear', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-linear-100L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 500, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-linear-100L-16.9M-20260812-233703', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 2498, 'eval_delay': 0, 'per_device_eval_batch_size': 1024, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-linear-100L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
|
| 19 |
+
2026-08-12 23:37:05,315 INFO MainThread:3978000 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 16934016 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14d9ca094510>>
|
| 20 |
+
2026-08-12 23:37:05,315 INFO MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
|
zain/Activation/wandb/run-20260812_213354-drnrn7sc/logs/debug-core.log
CHANGED
|
@@ -83,3 +83,10 @@
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 86 |
+
{"time":"2026-08-12T23:37:02.775675342Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 87 |
+
{"time":"2026-08-12T23:37:03.311916843Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 88 |
+
{"time":"2026-08-12T23:37:03.313411037Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"8u0k1nti","id":"5(@)"}
|
| 89 |
+
{"time":"2026-08-12T23:37:03.314038795Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"8u0k1nti","id":"5(@)"}
|
| 90 |
+
{"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
|
| 91 |
+
{"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
|
| 92 |
+
{"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
|
zain/Activation/wandb/run-20260812_213440-m4b216ej/logs/debug-core.log
CHANGED
|
@@ -83,3 +83,10 @@
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 86 |
+
{"time":"2026-08-12T23:37:02.775675342Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 87 |
+
{"time":"2026-08-12T23:37:03.311916843Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 88 |
+
{"time":"2026-08-12T23:37:03.313411037Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"8u0k1nti","id":"5(@)"}
|
| 89 |
+
{"time":"2026-08-12T23:37:03.314038795Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"8u0k1nti","id":"5(@)"}
|
| 90 |
+
{"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
|
| 91 |
+
{"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
|
| 92 |
+
{"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
|
zain/Activation/wandb/run-20260812_213624-1sryr5l2/logs/debug-core.log
CHANGED
|
@@ -83,3 +83,10 @@
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 86 |
+
{"time":"2026-08-12T23:37:02.775675342Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 87 |
+
{"time":"2026-08-12T23:37:03.311916843Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 88 |
+
{"time":"2026-08-12T23:37:03.313411037Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"8u0k1nti","id":"5(@)"}
|
| 89 |
+
{"time":"2026-08-12T23:37:03.314038795Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"8u0k1nti","id":"5(@)"}
|
| 90 |
+
{"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
|
| 91 |
+
{"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
|
| 92 |
+
{"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
|
zain/Activation/wandb/run-20260812_220132-25l266uo/logs/debug-core.log
CHANGED
|
@@ -83,3 +83,10 @@
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 86 |
+
{"time":"2026-08-12T23:37:02.775675342Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 87 |
+
{"time":"2026-08-12T23:37:03.311916843Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 88 |
+
{"time":"2026-08-12T23:37:03.313411037Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"8u0k1nti","id":"5(@)"}
|
| 89 |
+
{"time":"2026-08-12T23:37:03.314038795Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"8u0k1nti","id":"5(@)"}
|
| 90 |
+
{"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
|
| 91 |
+
{"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
|
| 92 |
+
{"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
|
zain/Activation/wandb/run-20260812_222706-8exldg55/logs/debug-core.log
CHANGED
|
@@ -83,3 +83,10 @@
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
{"time":"2026-08-12T23:23:26.521833126Z","level":"INFO","msg":"handleInformInit: received","streamId":"8u0k1nti","id":"5(@)"}
|
| 84 |
{"time":"2026-08-12T23:23:26.782624087Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u0k1nti","id":"5(@)"}
|
| 85 |
{"time":"2026-08-12T23:23:32.243586942Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 86 |
+
{"time":"2026-08-12T23:37:02.775675342Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 87 |
+
{"time":"2026-08-12T23:37:03.311916843Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"leu4u5ch9v5m"}
|
| 88 |
+
{"time":"2026-08-12T23:37:03.313411037Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"8u0k1nti","id":"5(@)"}
|
| 89 |
+
{"time":"2026-08-12T23:37:03.314038795Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"8u0k1nti","id":"5(@)"}
|
| 90 |
+
{"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
|
| 91 |
+
{"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
|
| 92 |
+
{"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
|