Training in progress, step 800, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
@@ -203,15 +203,15 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
203 |
|
204 |
The following `bitsandbytes` quantization config was used during training:
|
205 |
- quant_method: bitsandbytes
|
206 |
-
- load_in_8bit:
|
207 |
-
- load_in_4bit:
|
208 |
- llm_int8_threshold: 6.0
|
209 |
- llm_int8_skip_modules: None
|
210 |
- llm_int8_enable_fp32_cpu_offload: False
|
211 |
- llm_int8_has_fp16_weight: False
|
212 |
-
- bnb_4bit_quant_type:
|
213 |
- bnb_4bit_use_double_quant: False
|
214 |
-
- bnb_4bit_compute_dtype:
|
215 |
|
216 |
### Framework versions
|
217 |
|
|
|
203 |
|
204 |
The following `bitsandbytes` quantization config was used during training:
|
205 |
- quant_method: bitsandbytes
|
206 |
+
- load_in_8bit: False
|
207 |
+
- load_in_4bit: True
|
208 |
- llm_int8_threshold: 6.0
|
209 |
- llm_int8_skip_modules: None
|
210 |
- llm_int8_enable_fp32_cpu_offload: False
|
211 |
- llm_int8_has_fp16_weight: False
|
212 |
+
- bnb_4bit_quant_type: nf4
|
213 |
- bnb_4bit_use_double_quant: False
|
214 |
+
- bnb_4bit_compute_dtype: float16
|
215 |
|
216 |
### Framework versions
|
217 |
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 19669752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b4fc40c220ef1336a088c091921ce3a08a94338dab7a698fcd0f7a479d97673
|
3 |
size 19669752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39356997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f493a44ebab79adc759884587237cae3f5c8b0c5f8ce99d0924299d35b86ae26
|
3 |
size 39356997
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cca3a7099dea147630d4f997ed815413f0ae73f258d866a6a2fb054f2568bdf7
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -105,6 +105,20 @@
|
|
105 |
"eval_samples_per_second": 2.406,
|
106 |
"eval_steps_per_second": 0.302,
|
107 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 100,
|
@@ -112,7 +126,7 @@
|
|
112 |
"num_input_tokens_seen": 0,
|
113 |
"num_train_epochs": 5,
|
114 |
"save_steps": 100,
|
115 |
-
"total_flos":
|
116 |
"trial_name": null,
|
117 |
"trial_params": null
|
118 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0066964626312256,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-800",
|
4 |
+
"epoch": 1.0666666666666667,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
105 |
"eval_samples_per_second": 2.406,
|
106 |
"eval_steps_per_second": 0.302,
|
107 |
"step": 700
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.07,
|
111 |
+
"learning_rate": 0.0002,
|
112 |
+
"loss": 0.8346,
|
113 |
+
"step": 800
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.07,
|
117 |
+
"eval_loss": 1.0066964626312256,
|
118 |
+
"eval_runtime": 789.7964,
|
119 |
+
"eval_samples_per_second": 2.444,
|
120 |
+
"eval_steps_per_second": 0.306,
|
121 |
+
"step": 800
|
122 |
}
|
123 |
],
|
124 |
"logging_steps": 100,
|
|
|
126 |
"num_input_tokens_seen": 0,
|
127 |
"num_train_epochs": 5,
|
128 |
"save_steps": 100,
|
129 |
+
"total_flos": 2.0717810165526528e+17,
|
130 |
"trial_name": null,
|
131 |
"trial_params": null
|
132 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4283
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ccaec94438a927540ddcdb806612d7266ef4370543ba0ccb4abcda4aa43ca9a
|
3 |
size 4283
|