Training in progress, step 16400
Browse files- adapter_model.safetensors +1 -1
- last-checkpoint/README.md +1 -1
- last-checkpoint/adapter_config.json +3 -5
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +3 -17
- last-checkpoint/training_args.bin +1 -1
- trainer_log.jsonl +2 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 161533160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f91e3c5f21cf129551bcf7c69bf4d8d16a4ef7f114f3eb09634873a47bacc359
|
| 3 |
size 161533160
|
last-checkpoint/README.md
CHANGED
|
@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
-
- PEFT 0.
|
|
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
+
- PEFT 0.14.0
|
last-checkpoint/adapter_config.json
CHANGED
|
@@ -3,7 +3,6 @@
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen3-0.6B",
|
| 5 |
"bias": "none",
|
| 6 |
-
"corda_config": null,
|
| 7 |
"eva_config": null,
|
| 8 |
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
|
@@ -24,16 +23,15 @@
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
-
"q_proj",
|
| 28 |
"o_proj",
|
| 29 |
-
"gate_proj",
|
| 30 |
"down_proj",
|
| 31 |
-
"
|
| 32 |
"k_proj",
|
|
|
|
|
|
|
| 33 |
"up_proj"
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
-
"trainable_token_indices": null,
|
| 37 |
"use_dora": false,
|
| 38 |
"use_rslora": false
|
| 39 |
}
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen3-0.6B",
|
| 5 |
"bias": "none",
|
|
|
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
| 8 |
"fan_in_fan_out": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
| 26 |
"o_proj",
|
|
|
|
| 27 |
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
"k_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
"up_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 35 |
"use_dora": false,
|
| 36 |
"use_rslora": false
|
| 37 |
}
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 161533160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0895ef68999d4dfb943206c62b67cf1ef8c34e6d4531bbf6cbd0164f87b27fb
|
| 3 |
size 161533160
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 323292202
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e8dbf38539f29794be1d65b30108f9525bfcf2e332bab29d374c55513a7d620
|
| 3 |
size 323292202
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16605380cae58712eea4da8f07eab38182175aa614b73a71198f2f8f482fc46a
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 2.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2308,20 +2308,6 @@
|
|
| 2308 |
"learning_rate": 3.3847853001028495e-06,
|
| 2309 |
"loss": 0.2699,
|
| 2310 |
"step": 16200
|
| 2311 |
-
},
|
| 2312 |
-
{
|
| 2313 |
-
"epoch": 2.6903973509933774,
|
| 2314 |
-
"grad_norm": 1.1786317825317383,
|
| 2315 |
-
"learning_rate": 3.2127666818151046e-06,
|
| 2316 |
-
"loss": 0.2717,
|
| 2317 |
-
"step": 16250
|
| 2318 |
-
},
|
| 2319 |
-
{
|
| 2320 |
-
"epoch": 2.698675496688742,
|
| 2321 |
-
"grad_norm": 1.0810590982437134,
|
| 2322 |
-
"learning_rate": 3.045088789355488e-06,
|
| 2323 |
-
"loss": 0.277,
|
| 2324 |
-
"step": 16300
|
| 2325 |
}
|
| 2326 |
],
|
| 2327 |
"logging_steps": 50,
|
|
@@ -2341,7 +2327,7 @@
|
|
| 2341 |
"attributes": {}
|
| 2342 |
}
|
| 2343 |
},
|
| 2344 |
-
"total_flos": 1.
|
| 2345 |
"train_batch_size": 1,
|
| 2346 |
"trial_name": null,
|
| 2347 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.6821192052980134,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 16200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2308 |
"learning_rate": 3.3847853001028495e-06,
|
| 2309 |
"loss": 0.2699,
|
| 2310 |
"step": 16200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2311 |
}
|
| 2312 |
],
|
| 2313 |
"logging_steps": 50,
|
|
|
|
| 2327 |
"attributes": {}
|
| 2328 |
}
|
| 2329 |
},
|
| 2330 |
+
"total_flos": 1.2713713196020531e+17,
|
| 2331 |
"train_batch_size": 1,
|
| 2332 |
"trial_name": null,
|
| 2333 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03460364198bac94559385f580ca233415d6d940ccd70edd3903925ee0255ba2
|
| 3 |
size 5752
|
trainer_log.jsonl
CHANGED
|
@@ -1,2 +1,4 @@
|
|
| 1 |
{"current_steps": 16250, "total_steps": 18120, "loss": 0.2717, "lr": 3.2127666818151046e-06, "epoch": 2.6903973509933774, "percentage": 89.68, "elapsed_time": "0:05:28", "remaining_time": "0:00:37"}
|
| 2 |
{"current_steps": 16300, "total_steps": 18120, "loss": 0.277, "lr": 3.045088789355488e-06, "epoch": 2.698675496688742, "percentage": 89.96, "elapsed_time": "0:11:01", "remaining_time": "0:01:13"}
|
|
|
|
|
|
|
|
|
| 1 |
{"current_steps": 16250, "total_steps": 18120, "loss": 0.2717, "lr": 3.2127666818151046e-06, "epoch": 2.6903973509933774, "percentage": 89.68, "elapsed_time": "0:05:28", "remaining_time": "0:00:37"}
|
| 2 |
{"current_steps": 16300, "total_steps": 18120, "loss": 0.277, "lr": 3.045088789355488e-06, "epoch": 2.698675496688742, "percentage": 89.96, "elapsed_time": "0:11:01", "remaining_time": "0:01:13"}
|
| 3 |
+
{"current_steps": 16350, "total_steps": 18120, "loss": 0.2652, "lr": 2.8817671791847634e-06, "epoch": 2.706953642384106, "percentage": 90.23, "elapsed_time": "0:16:10", "remaining_time": "0:01:45"}
|
| 4 |
+
{"current_steps": 16400, "total_steps": 18120, "loss": 0.2617, "lr": 2.7228170036058153e-06, "epoch": 2.7152317880794703, "percentage": 90.51, "elapsed_time": "0:21:29", "remaining_time": "0:02:15"}
|