End of training
Browse files- README.md +14 -2
- all_results.json +16 -0
- eval_results.json +10 -0
- tokenizer.json +1 -6
- train_results.json +9 -0
- trainer_state.json +701 -0
README.md
CHANGED
|
@@ -3,11 +3,23 @@ license: other
|
|
| 3 |
base_model: Qwen/Qwen1.5-4B
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: lmind_hotpot_train8000_eval7405_v1_docidx_Qwen_Qwen1.5-4B_lora2
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
library_name: peft
|
| 12 |
---
|
| 13 |
|
|
@@ -16,7 +28,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# lmind_hotpot_train8000_eval7405_v1_docidx_Qwen_Qwen1.5-4B_lora2
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 1.0623
|
| 22 |
- Accuracy: 0.7692
|
|
|
|
| 3 |
base_model: Qwen/Qwen1.5-4B
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- tyzhu/lmind_hotpot_train8000_eval7405_v1_docidx
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: lmind_hotpot_train8000_eval7405_v1_docidx_Qwen_Qwen1.5-4B_lora2
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Causal Language Modeling
|
| 15 |
+
type: text-generation
|
| 16 |
+
dataset:
|
| 17 |
+
name: tyzhu/lmind_hotpot_train8000_eval7405_v1_docidx
|
| 18 |
+
type: tyzhu/lmind_hotpot_train8000_eval7405_v1_docidx
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.7691922246220302
|
| 23 |
library_name: peft
|
| 24 |
---
|
| 25 |
|
|
|
|
| 28 |
|
| 29 |
# lmind_hotpot_train8000_eval7405_v1_docidx_Qwen_Qwen1.5-4B_lora2
|
| 30 |
|
| 31 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on the tyzhu/lmind_hotpot_train8000_eval7405_v1_docidx dataset.
|
| 32 |
It achieves the following results on the evaluation set:
|
| 33 |
- Loss: 1.0623
|
| 34 |
- Accuracy: 0.7692
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.997021149836163,
|
| 3 |
+
"eval_accuracy": 0.7691922246220302,
|
| 4 |
+
"eval_loss": 1.0623269081115723,
|
| 5 |
+
"eval_runtime": 7.649,
|
| 6 |
+
"eval_samples": 500,
|
| 7 |
+
"eval_samples_per_second": 65.368,
|
| 8 |
+
"eval_steps_per_second": 8.236,
|
| 9 |
+
"perplexity": 2.8930951295301637,
|
| 10 |
+
"total_flos": 6.866381543623885e+17,
|
| 11 |
+
"train_loss": 1.1092717030903723,
|
| 12 |
+
"train_runtime": 19337.1025,
|
| 13 |
+
"train_samples": 26854,
|
| 14 |
+
"train_samples_per_second": 13.887,
|
| 15 |
+
"train_steps_per_second": 0.434
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.997021149836163,
|
| 3 |
+
"eval_accuracy": 0.7691922246220302,
|
| 4 |
+
"eval_loss": 1.0623269081115723,
|
| 5 |
+
"eval_runtime": 7.649,
|
| 6 |
+
"eval_samples": 500,
|
| 7 |
+
"eval_samples_per_second": 65.368,
|
| 8 |
+
"eval_steps_per_second": 8.236,
|
| 9 |
+
"perplexity": 2.8930951295301637
|
| 10 |
+
}
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.997021149836163,
|
| 3 |
+
"total_flos": 6.866381543623885e+17,
|
| 4 |
+
"train_loss": 1.1092717030903723,
|
| 5 |
+
"train_runtime": 19337.1025,
|
| 6 |
+
"train_samples": 26854,
|
| 7 |
+
"train_samples_per_second": 13.887,
|
| 8 |
+
"train_steps_per_second": 0.434
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,701 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.997021149836163,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8390,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11915400655347036,
|
| 13 |
+
"grad_norm": 0.24564065039157867,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 1.6916,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.23830801310694072,
|
| 20 |
+
"grad_norm": 0.2549617886543274,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 1.6213,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3574620196604111,
|
| 27 |
+
"grad_norm": 0.26466843485832214,
|
| 28 |
+
"learning_rate": 0.0001,
|
| 29 |
+
"loss": 1.6443,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.47661602621388144,
|
| 34 |
+
"grad_norm": 0.2397240847349167,
|
| 35 |
+
"learning_rate": 0.0001,
|
| 36 |
+
"loss": 1.6157,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5957700327673519,
|
| 41 |
+
"grad_norm": 0.24300818145275116,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 1.6087,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.7149240393208222,
|
| 48 |
+
"grad_norm": 0.2128152847290039,
|
| 49 |
+
"learning_rate": 0.0001,
|
| 50 |
+
"loss": 1.6163,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.8340780458742926,
|
| 55 |
+
"grad_norm": 0.24853849411010742,
|
| 56 |
+
"learning_rate": 0.0001,
|
| 57 |
+
"loss": 1.609,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.9532320524277629,
|
| 62 |
+
"grad_norm": 0.26104700565338135,
|
| 63 |
+
"learning_rate": 0.0001,
|
| 64 |
+
"loss": 1.6067,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9997021149836163,
|
| 69 |
+
"eval_accuracy": 0.7197408207343412,
|
| 70 |
+
"eval_loss": 1.8439931869506836,
|
| 71 |
+
"eval_runtime": 7.8863,
|
| 72 |
+
"eval_samples_per_second": 63.401,
|
| 73 |
+
"eval_steps_per_second": 7.989,
|
| 74 |
+
"step": 839
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0723860589812333,
|
| 78 |
+
"grad_norm": 0.26654207706451416,
|
| 79 |
+
"learning_rate": 0.0001,
|
| 80 |
+
"loss": 1.5707,
|
| 81 |
+
"step": 900
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.1915400655347037,
|
| 85 |
+
"grad_norm": 0.3084248900413513,
|
| 86 |
+
"learning_rate": 0.0001,
|
| 87 |
+
"loss": 1.546,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.310694072088174,
|
| 92 |
+
"grad_norm": 0.35963907837867737,
|
| 93 |
+
"learning_rate": 0.0001,
|
| 94 |
+
"loss": 1.5456,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.4298480786416443,
|
| 99 |
+
"grad_norm": 0.32188501954078674,
|
| 100 |
+
"learning_rate": 0.0001,
|
| 101 |
+
"loss": 1.5333,
|
| 102 |
+
"step": 1200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.5490020851951147,
|
| 106 |
+
"grad_norm": 0.32053473591804504,
|
| 107 |
+
"learning_rate": 0.0001,
|
| 108 |
+
"loss": 1.5506,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.668156091748585,
|
| 113 |
+
"grad_norm": 0.35408514738082886,
|
| 114 |
+
"learning_rate": 0.0001,
|
| 115 |
+
"loss": 1.5256,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.7873100983020556,
|
| 120 |
+
"grad_norm": 0.3224356770515442,
|
| 121 |
+
"learning_rate": 0.0001,
|
| 122 |
+
"loss": 1.5349,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.9064641048555258,
|
| 127 |
+
"grad_norm": 0.3134737014770508,
|
| 128 |
+
"learning_rate": 0.0001,
|
| 129 |
+
"loss": 1.5433,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.9994042299672325,
|
| 134 |
+
"eval_accuracy": 0.7246911447084233,
|
| 135 |
+
"eval_loss": 1.7660729885101318,
|
| 136 |
+
"eval_runtime": 7.8239,
|
| 137 |
+
"eval_samples_per_second": 63.907,
|
| 138 |
+
"eval_steps_per_second": 8.052,
|
| 139 |
+
"step": 1678
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.025618111408996,
|
| 143 |
+
"grad_norm": 0.32698601484298706,
|
| 144 |
+
"learning_rate": 0.0001,
|
| 145 |
+
"loss": 1.5237,
|
| 146 |
+
"step": 1700
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.1447721179624666,
|
| 150 |
+
"grad_norm": 0.4822945296764374,
|
| 151 |
+
"learning_rate": 0.0001,
|
| 152 |
+
"loss": 1.4085,
|
| 153 |
+
"step": 1800
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.2639261245159368,
|
| 157 |
+
"grad_norm": 0.43997159600257874,
|
| 158 |
+
"learning_rate": 0.0001,
|
| 159 |
+
"loss": 1.4227,
|
| 160 |
+
"step": 1900
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.3830801310694074,
|
| 164 |
+
"grad_norm": 0.4469866156578064,
|
| 165 |
+
"learning_rate": 0.0001,
|
| 166 |
+
"loss": 1.4325,
|
| 167 |
+
"step": 2000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.5022341376228776,
|
| 171 |
+
"grad_norm": 0.44795843958854675,
|
| 172 |
+
"learning_rate": 0.0001,
|
| 173 |
+
"loss": 1.4266,
|
| 174 |
+
"step": 2100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.621388144176348,
|
| 178 |
+
"grad_norm": 0.41753217577934265,
|
| 179 |
+
"learning_rate": 0.0001,
|
| 180 |
+
"loss": 1.4235,
|
| 181 |
+
"step": 2200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.7405421507298184,
|
| 185 |
+
"grad_norm": 0.45843449234962463,
|
| 186 |
+
"learning_rate": 0.0001,
|
| 187 |
+
"loss": 1.4123,
|
| 188 |
+
"step": 2300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.8596961572832886,
|
| 192 |
+
"grad_norm": 0.5280742049217224,
|
| 193 |
+
"learning_rate": 0.0001,
|
| 194 |
+
"loss": 1.4162,
|
| 195 |
+
"step": 2400
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.978850163836759,
|
| 199 |
+
"grad_norm": 0.5003345012664795,
|
| 200 |
+
"learning_rate": 0.0001,
|
| 201 |
+
"loss": 1.4167,
|
| 202 |
+
"step": 2500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.999106344950849,
|
| 206 |
+
"eval_accuracy": 0.7309719222462203,
|
| 207 |
+
"eval_loss": 1.6454776525497437,
|
| 208 |
+
"eval_runtime": 7.8863,
|
| 209 |
+
"eval_samples_per_second": 63.401,
|
| 210 |
+
"eval_steps_per_second": 7.989,
|
| 211 |
+
"step": 2517
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.0980041703902295,
|
| 215 |
+
"grad_norm": 0.5184714794158936,
|
| 216 |
+
"learning_rate": 0.0001,
|
| 217 |
+
"loss": 1.3029,
|
| 218 |
+
"step": 2600
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.2171581769436997,
|
| 222 |
+
"grad_norm": 0.611228883266449,
|
| 223 |
+
"learning_rate": 0.0001,
|
| 224 |
+
"loss": 1.2788,
|
| 225 |
+
"step": 2700
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.33631218349717,
|
| 229 |
+
"grad_norm": 0.538593590259552,
|
| 230 |
+
"learning_rate": 0.0001,
|
| 231 |
+
"loss": 1.2949,
|
| 232 |
+
"step": 2800
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.4554661900506405,
|
| 236 |
+
"grad_norm": 0.5769683122634888,
|
| 237 |
+
"learning_rate": 0.0001,
|
| 238 |
+
"loss": 1.2816,
|
| 239 |
+
"step": 2900
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.5746201966041107,
|
| 243 |
+
"grad_norm": 0.541022002696991,
|
| 244 |
+
"learning_rate": 0.0001,
|
| 245 |
+
"loss": 1.2787,
|
| 246 |
+
"step": 3000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.6937742031575813,
|
| 250 |
+
"grad_norm": 0.5838562250137329,
|
| 251 |
+
"learning_rate": 0.0001,
|
| 252 |
+
"loss": 1.299,
|
| 253 |
+
"step": 3100
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.8129282097110515,
|
| 257 |
+
"grad_norm": 0.583423912525177,
|
| 258 |
+
"learning_rate": 0.0001,
|
| 259 |
+
"loss": 1.2967,
|
| 260 |
+
"step": 3200
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.932082216264522,
|
| 264 |
+
"grad_norm": 0.5817753672599792,
|
| 265 |
+
"learning_rate": 0.0001,
|
| 266 |
+
"loss": 1.2948,
|
| 267 |
+
"step": 3300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.0,
|
| 271 |
+
"eval_accuracy": 0.736622030237581,
|
| 272 |
+
"eval_loss": 1.5393506288528442,
|
| 273 |
+
"eval_runtime": 7.705,
|
| 274 |
+
"eval_samples_per_second": 64.893,
|
| 275 |
+
"eval_steps_per_second": 8.177,
|
| 276 |
+
"step": 3357
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.051236222817992,
|
| 280 |
+
"grad_norm": 0.661818265914917,
|
| 281 |
+
"learning_rate": 0.0001,
|
| 282 |
+
"loss": 1.2282,
|
| 283 |
+
"step": 3400
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.1703902293714625,
|
| 287 |
+
"grad_norm": 0.6072232723236084,
|
| 288 |
+
"learning_rate": 0.0001,
|
| 289 |
+
"loss": 1.1362,
|
| 290 |
+
"step": 3500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.289544235924933,
|
| 294 |
+
"grad_norm": 0.6120555996894836,
|
| 295 |
+
"learning_rate": 0.0001,
|
| 296 |
+
"loss": 1.1453,
|
| 297 |
+
"step": 3600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.408698242478403,
|
| 301 |
+
"grad_norm": 0.698825478553772,
|
| 302 |
+
"learning_rate": 0.0001,
|
| 303 |
+
"loss": 1.1467,
|
| 304 |
+
"step": 3700
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.5278522490318736,
|
| 308 |
+
"grad_norm": 0.6432230472564697,
|
| 309 |
+
"learning_rate": 0.0001,
|
| 310 |
+
"loss": 1.1593,
|
| 311 |
+
"step": 3800
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.647006255585344,
|
| 315 |
+
"grad_norm": 0.9182979464530945,
|
| 316 |
+
"learning_rate": 0.0001,
|
| 317 |
+
"loss": 1.1709,
|
| 318 |
+
"step": 3900
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.766160262138815,
|
| 322 |
+
"grad_norm": 0.6992977857589722,
|
| 323 |
+
"learning_rate": 0.0001,
|
| 324 |
+
"loss": 1.1674,
|
| 325 |
+
"step": 4000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.885314268692285,
|
| 329 |
+
"grad_norm": 0.6830582022666931,
|
| 330 |
+
"learning_rate": 0.0001,
|
| 331 |
+
"loss": 1.1715,
|
| 332 |
+
"step": 4100
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.9997021149836165,
|
| 336 |
+
"eval_accuracy": 0.7422375809935206,
|
| 337 |
+
"eval_loss": 1.4463233947753906,
|
| 338 |
+
"eval_runtime": 7.7567,
|
| 339 |
+
"eval_samples_per_second": 64.461,
|
| 340 |
+
"eval_steps_per_second": 8.122,
|
| 341 |
+
"step": 4196
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 5.004468275245755,
|
| 345 |
+
"grad_norm": 0.5924903750419617,
|
| 346 |
+
"learning_rate": 0.0001,
|
| 347 |
+
"loss": 1.1816,
|
| 348 |
+
"step": 4200
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 5.123622281799226,
|
| 352 |
+
"grad_norm": 0.8615913987159729,
|
| 353 |
+
"learning_rate": 0.0001,
|
| 354 |
+
"loss": 1.0065,
|
| 355 |
+
"step": 4300
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 5.242776288352696,
|
| 359 |
+
"grad_norm": 0.8048379421234131,
|
| 360 |
+
"learning_rate": 0.0001,
|
| 361 |
+
"loss": 1.0146,
|
| 362 |
+
"step": 4400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 5.361930294906166,
|
| 366 |
+
"grad_norm": 0.7855103015899658,
|
| 367 |
+
"learning_rate": 0.0001,
|
| 368 |
+
"loss": 1.0196,
|
| 369 |
+
"step": 4500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 5.481084301459637,
|
| 373 |
+
"grad_norm": 0.8682273626327515,
|
| 374 |
+
"learning_rate": 0.0001,
|
| 375 |
+
"loss": 1.0334,
|
| 376 |
+
"step": 4600
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 5.600238308013107,
|
| 380 |
+
"grad_norm": 0.8534315228462219,
|
| 381 |
+
"learning_rate": 0.0001,
|
| 382 |
+
"loss": 1.0415,
|
| 383 |
+
"step": 4700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 5.719392314566577,
|
| 387 |
+
"grad_norm": 0.7905874252319336,
|
| 388 |
+
"learning_rate": 0.0001,
|
| 389 |
+
"loss": 1.0472,
|
| 390 |
+
"step": 4800
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.838546321120048,
|
| 394 |
+
"grad_norm": 0.7829225659370422,
|
| 395 |
+
"learning_rate": 0.0001,
|
| 396 |
+
"loss": 1.0353,
|
| 397 |
+
"step": 4900
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 5.957700327673518,
|
| 401 |
+
"grad_norm": 0.7980929613113403,
|
| 402 |
+
"learning_rate": 0.0001,
|
| 403 |
+
"loss": 1.0458,
|
| 404 |
+
"step": 5000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.999404229967233,
|
| 408 |
+
"eval_accuracy": 0.7483671706263499,
|
| 409 |
+
"eval_loss": 1.353654384613037,
|
| 410 |
+
"eval_runtime": 7.9987,
|
| 411 |
+
"eval_samples_per_second": 62.51,
|
| 412 |
+
"eval_steps_per_second": 7.876,
|
| 413 |
+
"step": 5035
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 6.076854334226988,
|
| 417 |
+
"grad_norm": 0.7904637455940247,
|
| 418 |
+
"learning_rate": 0.0001,
|
| 419 |
+
"loss": 0.9339,
|
| 420 |
+
"step": 5100
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 6.196008340780459,
|
| 424 |
+
"grad_norm": 1.046057105064392,
|
| 425 |
+
"learning_rate": 0.0001,
|
| 426 |
+
"loss": 0.8833,
|
| 427 |
+
"step": 5200
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 6.31516234733393,
|
| 431 |
+
"grad_norm": 0.8678649663925171,
|
| 432 |
+
"learning_rate": 0.0001,
|
| 433 |
+
"loss": 0.8899,
|
| 434 |
+
"step": 5300
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.434316353887399,
|
| 438 |
+
"grad_norm": 0.9677824378013611,
|
| 439 |
+
"learning_rate": 0.0001,
|
| 440 |
+
"loss": 0.9211,
|
| 441 |
+
"step": 5400
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 6.55347036044087,
|
| 445 |
+
"grad_norm": 0.9737918376922607,
|
| 446 |
+
"learning_rate": 0.0001,
|
| 447 |
+
"loss": 0.9206,
|
| 448 |
+
"step": 5500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 6.67262436699434,
|
| 452 |
+
"grad_norm": 0.8853780627250671,
|
| 453 |
+
"learning_rate": 0.0001,
|
| 454 |
+
"loss": 0.9225,
|
| 455 |
+
"step": 5600
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 6.79177837354781,
|
| 459 |
+
"grad_norm": 0.9523513913154602,
|
| 460 |
+
"learning_rate": 0.0001,
|
| 461 |
+
"loss": 0.9163,
|
| 462 |
+
"step": 5700
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 6.910932380101281,
|
| 466 |
+
"grad_norm": 0.9134466648101807,
|
| 467 |
+
"learning_rate": 0.0001,
|
| 468 |
+
"loss": 0.9357,
|
| 469 |
+
"step": 5800
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 6.999106344950849,
|
| 473 |
+
"eval_accuracy": 0.7545961123110151,
|
| 474 |
+
"eval_loss": 1.2455778121948242,
|
| 475 |
+
"eval_runtime": 7.6574,
|
| 476 |
+
"eval_samples_per_second": 65.296,
|
| 477 |
+
"eval_steps_per_second": 8.227,
|
| 478 |
+
"step": 5874
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 7.030086386654752,
|
| 482 |
+
"grad_norm": 1.020137906074524,
|
| 483 |
+
"learning_rate": 0.0001,
|
| 484 |
+
"loss": 0.8909,
|
| 485 |
+
"step": 5900
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 7.149240393208221,
|
| 489 |
+
"grad_norm": 0.9680564403533936,
|
| 490 |
+
"learning_rate": 0.0001,
|
| 491 |
+
"loss": 0.7683,
|
| 492 |
+
"step": 6000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.268394399761692,
|
| 496 |
+
"grad_norm": 0.9959320425987244,
|
| 497 |
+
"learning_rate": 0.0001,
|
| 498 |
+
"loss": 0.7802,
|
| 499 |
+
"step": 6100
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.387548406315163,
|
| 503 |
+
"grad_norm": 1.0101680755615234,
|
| 504 |
+
"learning_rate": 0.0001,
|
| 505 |
+
"loss": 0.7758,
|
| 506 |
+
"step": 6200
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.506702412868632,
|
| 510 |
+
"grad_norm": 0.929568886756897,
|
| 511 |
+
"learning_rate": 0.0001,
|
| 512 |
+
"loss": 0.8111,
|
| 513 |
+
"step": 6300
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.625856419422103,
|
| 517 |
+
"grad_norm": 1.101192593574524,
|
| 518 |
+
"learning_rate": 0.0001,
|
| 519 |
+
"loss": 0.8047,
|
| 520 |
+
"step": 6400
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.745010425975574,
|
| 524 |
+
"grad_norm": 1.0534611940383911,
|
| 525 |
+
"learning_rate": 0.0001,
|
| 526 |
+
"loss": 0.8168,
|
| 527 |
+
"step": 6500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.864164432529043,
|
| 531 |
+
"grad_norm": 1.08072829246521,
|
| 532 |
+
"learning_rate": 0.0001,
|
| 533 |
+
"loss": 0.8178,
|
| 534 |
+
"step": 6600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.983318439082514,
|
| 538 |
+
"grad_norm": 1.2470301389694214,
|
| 539 |
+
"learning_rate": 0.0001,
|
| 540 |
+
"loss": 0.8269,
|
| 541 |
+
"step": 6700
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 8.0,
|
| 545 |
+
"eval_accuracy": 0.7598142548596112,
|
| 546 |
+
"eval_loss": 1.1735292673110962,
|
| 547 |
+
"eval_runtime": 7.6157,
|
| 548 |
+
"eval_samples_per_second": 65.654,
|
| 549 |
+
"eval_steps_per_second": 8.272,
|
| 550 |
+
"step": 6714
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 8.102472445635984,
|
| 554 |
+
"grad_norm": 1.0507800579071045,
|
| 555 |
+
"learning_rate": 0.0001,
|
| 556 |
+
"loss": 0.6826,
|
| 557 |
+
"step": 6800
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 8.221626452189454,
|
| 561 |
+
"grad_norm": 0.966494083404541,
|
| 562 |
+
"learning_rate": 0.0001,
|
| 563 |
+
"loss": 0.6672,
|
| 564 |
+
"step": 6900
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 8.340780458742925,
|
| 568 |
+
"grad_norm": 1.0983446836471558,
|
| 569 |
+
"learning_rate": 0.0001,
|
| 570 |
+
"loss": 0.6883,
|
| 571 |
+
"step": 7000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 8.459934465296396,
|
| 575 |
+
"grad_norm": 1.1256661415100098,
|
| 576 |
+
"learning_rate": 0.0001,
|
| 577 |
+
"loss": 0.6951,
|
| 578 |
+
"step": 7100
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 8.579088471849866,
|
| 582 |
+
"grad_norm": 1.2311198711395264,
|
| 583 |
+
"learning_rate": 0.0001,
|
| 584 |
+
"loss": 0.7196,
|
| 585 |
+
"step": 7200
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 8.698242478403337,
|
| 589 |
+
"grad_norm": 1.108267068862915,
|
| 590 |
+
"learning_rate": 0.0001,
|
| 591 |
+
"loss": 0.7081,
|
| 592 |
+
"step": 7300
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 8.817396484956806,
|
| 596 |
+
"grad_norm": 1.1294405460357666,
|
| 597 |
+
"learning_rate": 0.0001,
|
| 598 |
+
"loss": 0.7131,
|
| 599 |
+
"step": 7400
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 8.936550491510276,
|
| 603 |
+
"grad_norm": 1.301544189453125,
|
| 604 |
+
"learning_rate": 0.0001,
|
| 605 |
+
"loss": 0.7262,
|
| 606 |
+
"step": 7500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 8.999702114983616,
|
| 610 |
+
"eval_accuracy": 0.7649460043196544,
|
| 611 |
+
"eval_loss": 1.0966144800186157,
|
| 612 |
+
"eval_runtime": 7.7663,
|
| 613 |
+
"eval_samples_per_second": 64.381,
|
| 614 |
+
"eval_steps_per_second": 8.112,
|
| 615 |
+
"step": 7553
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 9.055704498063747,
|
| 619 |
+
"grad_norm": 1.3238133192062378,
|
| 620 |
+
"learning_rate": 0.0001,
|
| 621 |
+
"loss": 0.6592,
|
| 622 |
+
"step": 7600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 9.174858504617218,
|
| 626 |
+
"grad_norm": 0.9897598028182983,
|
| 627 |
+
"learning_rate": 0.0001,
|
| 628 |
+
"loss": 0.5839,
|
| 629 |
+
"step": 7700
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 9.294012511170688,
|
| 633 |
+
"grad_norm": 1.2646971940994263,
|
| 634 |
+
"learning_rate": 0.0001,
|
| 635 |
+
"loss": 0.6008,
|
| 636 |
+
"step": 7800
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 9.413166517724159,
|
| 640 |
+
"grad_norm": 1.1842299699783325,
|
| 641 |
+
"learning_rate": 0.0001,
|
| 642 |
+
"loss": 0.6062,
|
| 643 |
+
"step": 7900
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 9.53232052427763,
|
| 647 |
+
"grad_norm": 1.2886223793029785,
|
| 648 |
+
"learning_rate": 0.0001,
|
| 649 |
+
"loss": 0.6136,
|
| 650 |
+
"step": 8000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 9.651474530831099,
|
| 654 |
+
"grad_norm": 1.2469590902328491,
|
| 655 |
+
"learning_rate": 0.0001,
|
| 656 |
+
"loss": 0.6217,
|
| 657 |
+
"step": 8100
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 9.77062853738457,
|
| 661 |
+
"grad_norm": 1.202868103981018,
|
| 662 |
+
"learning_rate": 0.0001,
|
| 663 |
+
"loss": 0.6322,
|
| 664 |
+
"step": 8200
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 9.88978254393804,
|
| 668 |
+
"grad_norm": 1.3775478601455688,
|
| 669 |
+
"learning_rate": 0.0001,
|
| 670 |
+
"loss": 0.6381,
|
| 671 |
+
"step": 8300
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 9.997021149836163,
|
| 675 |
+
"eval_accuracy": 0.7691922246220302,
|
| 676 |
+
"eval_loss": 1.0623269081115723,
|
| 677 |
+
"eval_runtime": 7.6207,
|
| 678 |
+
"eval_samples_per_second": 65.611,
|
| 679 |
+
"eval_steps_per_second": 8.267,
|
| 680 |
+
"step": 8390
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 9.997021149836163,
|
| 684 |
+
"step": 8390,
|
| 685 |
+
"total_flos": 6.866381543623885e+17,
|
| 686 |
+
"train_loss": 1.1092717030903723,
|
| 687 |
+
"train_runtime": 19337.1025,
|
| 688 |
+
"train_samples_per_second": 13.887,
|
| 689 |
+
"train_steps_per_second": 0.434
|
| 690 |
+
}
|
| 691 |
+
],
|
| 692 |
+
"logging_steps": 100,
|
| 693 |
+
"max_steps": 8390,
|
| 694 |
+
"num_input_tokens_seen": 0,
|
| 695 |
+
"num_train_epochs": 10,
|
| 696 |
+
"save_steps": 500,
|
| 697 |
+
"total_flos": 6.866381543623885e+17,
|
| 698 |
+
"train_batch_size": 1,
|
| 699 |
+
"trial_name": null,
|
| 700 |
+
"trial_params": null
|
| 701 |
+
}
|