End of training
Browse files- README.md +5 -3
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +10 -0
- trainer_state.json +912 -0
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/flan-t5-xl
|
| 5 |
tags:
|
|
@@ -14,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# flan-t5-xl-summary-map-reduce-1024
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Num Input Tokens Seen:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
license: apache-2.0
|
| 6 |
base_model: google/flan-t5-xl
|
| 7 |
tags:
|
|
|
|
| 16 |
|
| 17 |
# flan-t5-xl-summary-map-reduce-1024
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on the pszemraj/summary-map-reduce dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6039
|
| 22 |
+
- Num Input Tokens Seen: 7138765
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.994705174488568,
|
| 3 |
+
"eval_loss": 0.6039194464683533,
|
| 4 |
+
"eval_runtime": 6.2075,
|
| 5 |
+
"eval_samples": 150,
|
| 6 |
+
"eval_samples_per_second": 24.164,
|
| 7 |
+
"eval_steps_per_second": 12.082,
|
| 8 |
+
"num_input_tokens_seen": 7138765,
|
| 9 |
+
"total_flos": 1.1924408841596928e+17,
|
| 10 |
+
"train_loss": 0.744573145759612,
|
| 11 |
+
"train_runtime": 5797.4674,
|
| 12 |
+
"train_samples": 16619,
|
| 13 |
+
"train_samples_per_second": 5.733,
|
| 14 |
+
"train_steps_per_second": 0.089
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.994705174488568,
|
| 3 |
+
"eval_loss": 0.6039194464683533,
|
| 4 |
+
"eval_runtime": 6.2075,
|
| 5 |
+
"eval_samples": 150,
|
| 6 |
+
"eval_samples_per_second": 24.164,
|
| 7 |
+
"eval_steps_per_second": 12.082,
|
| 8 |
+
"num_input_tokens_seen": 7138765
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.994705174488568,
|
| 3 |
+
"num_input_tokens_seen": 7138765,
|
| 4 |
+
"total_flos": 1.1924408841596928e+17,
|
| 5 |
+
"train_loss": 0.744573145759612,
|
| 6 |
+
"train_runtime": 5797.4674,
|
| 7 |
+
"train_samples": 16619,
|
| 8 |
+
"train_samples_per_second": 5.733,
|
| 9 |
+
"train_steps_per_second": 0.089
|
| 10 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,912 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.994705174488568,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 518,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.019253910950661854,
|
| 13 |
+
"grad_norm": 2.4829742908477783,
|
| 14 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 15 |
+
"loss": 1.3128,
|
| 16 |
+
"num_input_tokens_seen": 67662,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03850782190132371,
|
| 21 |
+
"grad_norm": 1.7913451194763184,
|
| 22 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 23 |
+
"loss": 1.2288,
|
| 24 |
+
"num_input_tokens_seen": 133986,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.05776173285198556,
|
| 29 |
+
"grad_norm": 1.1510990858078003,
|
| 30 |
+
"learning_rate": 4.615384615384615e-05,
|
| 31 |
+
"loss": 1.0893,
|
| 32 |
+
"num_input_tokens_seen": 202626,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07701564380264742,
|
| 37 |
+
"grad_norm": 0.7305760383605957,
|
| 38 |
+
"learning_rate": 6.153846153846155e-05,
|
| 39 |
+
"loss": 1.0228,
|
| 40 |
+
"num_input_tokens_seen": 264348,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.09626955475330927,
|
| 45 |
+
"grad_norm": 0.84750896692276,
|
| 46 |
+
"learning_rate": 7.692307692307693e-05,
|
| 47 |
+
"loss": 0.9562,
|
| 48 |
+
"num_input_tokens_seen": 333586,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.11552346570397112,
|
| 53 |
+
"grad_norm": 0.7335062623023987,
|
| 54 |
+
"learning_rate": 7.998695344323427e-05,
|
| 55 |
+
"loss": 0.9524,
|
| 56 |
+
"num_input_tokens_seen": 395406,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.13477737665463296,
|
| 61 |
+
"grad_norm": 0.948805034160614,
|
| 62 |
+
"learning_rate": 7.993396639212965e-05,
|
| 63 |
+
"loss": 0.8957,
|
| 64 |
+
"num_input_tokens_seen": 467462,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15403128760529483,
|
| 69 |
+
"grad_norm": 0.7413954734802246,
|
| 70 |
+
"learning_rate": 7.984027740137819e-05,
|
| 71 |
+
"loss": 0.8737,
|
| 72 |
+
"num_input_tokens_seen": 543588,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.17328519855595667,
|
| 77 |
+
"grad_norm": 0.7637290954589844,
|
| 78 |
+
"learning_rate": 7.970598196171101e-05,
|
| 79 |
+
"loss": 0.8871,
|
| 80 |
+
"num_input_tokens_seen": 613352,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.19253910950661854,
|
| 85 |
+
"grad_norm": 0.761428952217102,
|
| 86 |
+
"learning_rate": 7.953121695121395e-05,
|
| 87 |
+
"loss": 0.8344,
|
| 88 |
+
"num_input_tokens_seen": 681318,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.21179302045728038,
|
| 93 |
+
"grad_norm": 0.7143028974533081,
|
| 94 |
+
"learning_rate": 7.93161604958172e-05,
|
| 95 |
+
"loss": 0.8389,
|
| 96 |
+
"num_input_tokens_seen": 753680,
|
| 97 |
+
"step": 55
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.23104693140794225,
|
| 101 |
+
"grad_norm": 0.6739410758018494,
|
| 102 |
+
"learning_rate": 7.906103178774378e-05,
|
| 103 |
+
"loss": 0.8587,
|
| 104 |
+
"num_input_tokens_seen": 820164,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.2503008423586041,
|
| 109 |
+
"grad_norm": 0.723397433757782,
|
| 110 |
+
"learning_rate": 7.876609086210207e-05,
|
| 111 |
+
"loss": 0.842,
|
| 112 |
+
"num_input_tokens_seen": 888138,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.2695547533092659,
|
| 117 |
+
"grad_norm": 0.66191166639328,
|
| 118 |
+
"learning_rate": 7.843163833184991e-05,
|
| 119 |
+
"loss": 0.816,
|
| 120 |
+
"num_input_tokens_seen": 958314,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2888086642599278,
|
| 125 |
+
"grad_norm": 0.6319432854652405,
|
| 126 |
+
"learning_rate": 7.80580150814005e-05,
|
| 127 |
+
"loss": 0.8416,
|
| 128 |
+
"num_input_tokens_seen": 1030194,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.30806257521058966,
|
| 133 |
+
"grad_norm": 0.7031162977218628,
|
| 134 |
+
"learning_rate": 7.764560191918247e-05,
|
| 135 |
+
"loss": 0.8179,
|
| 136 |
+
"num_input_tokens_seen": 1095740,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.32731648616125153,
|
| 141 |
+
"grad_norm": 0.6904546618461609,
|
| 142 |
+
"learning_rate": 7.719481918950805e-05,
|
| 143 |
+
"loss": 0.802,
|
| 144 |
+
"num_input_tokens_seen": 1163928,
|
| 145 |
+
"step": 85
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.34657039711191334,
|
| 149 |
+
"grad_norm": 0.6699234247207642,
|
| 150 |
+
"learning_rate": 7.670612634414513e-05,
|
| 151 |
+
"loss": 0.8093,
|
| 152 |
+
"num_input_tokens_seen": 1233316,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.3658243080625752,
|
| 157 |
+
"grad_norm": 0.6710209250450134,
|
| 158 |
+
"learning_rate": 7.618002147402967e-05,
|
| 159 |
+
"loss": 0.8349,
|
| 160 |
+
"num_input_tokens_seen": 1298016,
|
| 161 |
+
"step": 95
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.3850782190132371,
|
| 165 |
+
"grad_norm": 0.6232579946517944,
|
| 166 |
+
"learning_rate": 7.561704080159603e-05,
|
| 167 |
+
"loss": 0.8172,
|
| 168 |
+
"num_input_tokens_seen": 1364870,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.3850782190132371,
|
| 173 |
+
"eval_loss": 0.6644170880317688,
|
| 174 |
+
"eval_runtime": 5.7343,
|
| 175 |
+
"eval_samples_per_second": 26.158,
|
| 176 |
+
"eval_steps_per_second": 13.079,
|
| 177 |
+
"num_input_tokens_seen": 1364870,
|
| 178 |
+
"step": 100
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4043321299638989,
|
| 182 |
+
"grad_norm": 0.6807074546813965,
|
| 183 |
+
"learning_rate": 7.50177581342423e-05,
|
| 184 |
+
"loss": 0.8169,
|
| 185 |
+
"num_input_tokens_seen": 1437970,
|
| 186 |
+
"step": 105
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.42358604091456076,
|
| 190 |
+
"grad_norm": 0.6546260714530945,
|
| 191 |
+
"learning_rate": 7.438278427948805e-05,
|
| 192 |
+
"loss": 0.817,
|
| 193 |
+
"num_input_tokens_seen": 1512200,
|
| 194 |
+
"step": 110
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.4428399518652226,
|
| 198 |
+
"grad_norm": 0.7773868441581726,
|
| 199 |
+
"learning_rate": 7.371276642242027e-05,
|
| 200 |
+
"loss": 0.8038,
|
| 201 |
+
"num_input_tokens_seen": 1592192,
|
| 202 |
+
"step": 115
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.4620938628158845,
|
| 206 |
+
"grad_norm": 0.6242259740829468,
|
| 207 |
+
"learning_rate": 7.300838746606224e-05,
|
| 208 |
+
"loss": 0.7998,
|
| 209 |
+
"num_input_tokens_seen": 1656614,
|
| 210 |
+
"step": 120
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.4813477737665463,
|
| 214 |
+
"grad_norm": 0.5981661677360535,
|
| 215 |
+
"learning_rate": 7.227036533533753e-05,
|
| 216 |
+
"loss": 0.8069,
|
| 217 |
+
"num_input_tokens_seen": 1731572,
|
| 218 |
+
"step": 125
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.5006016847172082,
|
| 222 |
+
"grad_norm": 0.6073790788650513,
|
| 223 |
+
"learning_rate": 7.149945224533863e-05,
|
| 224 |
+
"loss": 0.7847,
|
| 225 |
+
"num_input_tokens_seen": 1797496,
|
| 226 |
+
"step": 130
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.51985559566787,
|
| 230 |
+
"grad_norm": 0.6308819055557251,
|
| 231 |
+
"learning_rate": 7.069643393464592e-05,
|
| 232 |
+
"loss": 0.805,
|
| 233 |
+
"num_input_tokens_seen": 1860442,
|
| 234 |
+
"step": 135
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5391095066185319,
|
| 238 |
+
"grad_norm": 0.7135605216026306,
|
| 239 |
+
"learning_rate": 6.986212886447851e-05,
|
| 240 |
+
"loss": 0.7924,
|
| 241 |
+
"num_input_tokens_seen": 1924462,
|
| 242 |
+
"step": 140
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.5583634175691937,
|
| 246 |
+
"grad_norm": 0.6704626083374023,
|
| 247 |
+
"learning_rate": 6.899738738449313e-05,
|
| 248 |
+
"loss": 0.7926,
|
| 249 |
+
"num_input_tokens_seen": 1994714,
|
| 250 |
+
"step": 145
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.5776173285198556,
|
| 254 |
+
"grad_norm": 0.6295877695083618,
|
| 255 |
+
"learning_rate": 6.81030908660813e-05,
|
| 256 |
+
"loss": 0.7977,
|
| 257 |
+
"num_input_tokens_seen": 2064324,
|
| 258 |
+
"step": 150
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.5968712394705175,
|
| 262 |
+
"grad_norm": 0.5767641067504883,
|
| 263 |
+
"learning_rate": 6.718015080404824e-05,
|
| 264 |
+
"loss": 0.7912,
|
| 265 |
+
"num_input_tokens_seen": 2141534,
|
| 266 |
+
"step": 155
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.6161251504211793,
|
| 270 |
+
"grad_norm": 0.6175399422645569,
|
| 271 |
+
"learning_rate": 6.622950788758907e-05,
|
| 272 |
+
"loss": 0.7781,
|
| 273 |
+
"num_input_tokens_seen": 2205388,
|
| 274 |
+
"step": 160
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.6353790613718412,
|
| 278 |
+
"grad_norm": 0.7159196734428406,
|
| 279 |
+
"learning_rate": 6.525213104150908e-05,
|
| 280 |
+
"loss": 0.7733,
|
| 281 |
+
"num_input_tokens_seen": 2268804,
|
| 282 |
+
"step": 165
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6546329723225031,
|
| 286 |
+
"grad_norm": 0.6217786073684692,
|
| 287 |
+
"learning_rate": 6.424901643866553e-05,
|
| 288 |
+
"loss": 0.7842,
|
| 289 |
+
"num_input_tokens_seen": 2342992,
|
| 290 |
+
"step": 170
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6738868832731648,
|
| 294 |
+
"grad_norm": 0.7792349457740784,
|
| 295 |
+
"learning_rate": 6.32211864846372e-05,
|
| 296 |
+
"loss": 0.7876,
|
| 297 |
+
"num_input_tokens_seen": 2412156,
|
| 298 |
+
"step": 175
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.6931407942238267,
|
| 302 |
+
"grad_norm": 0.6551147699356079,
|
| 303 |
+
"learning_rate": 6.2169688775657e-05,
|
| 304 |
+
"loss": 0.7783,
|
| 305 |
+
"num_input_tokens_seen": 2482798,
|
| 306 |
+
"step": 180
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.7123947051744886,
|
| 310 |
+
"grad_norm": 0.6172861456871033,
|
| 311 |
+
"learning_rate": 6.109559503086918e-05,
|
| 312 |
+
"loss": 0.7666,
|
| 313 |
+
"num_input_tokens_seen": 2546172,
|
| 314 |
+
"step": 185
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.7316486161251504,
|
| 318 |
+
"grad_norm": 0.6506001949310303,
|
| 319 |
+
"learning_rate": 6.000000000000001e-05,
|
| 320 |
+
"loss": 0.7682,
|
| 321 |
+
"num_input_tokens_seen": 2611840,
|
| 322 |
+
"step": 190
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.7509025270758123,
|
| 326 |
+
"grad_norm": 0.582889974117279,
|
| 327 |
+
"learning_rate": 5.888402034755471e-05,
|
| 328 |
+
"loss": 0.763,
|
| 329 |
+
"num_input_tokens_seen": 2680788,
|
| 330 |
+
"step": 195
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.7701564380264742,
|
| 334 |
+
"grad_norm": 0.6109009385108948,
|
| 335 |
+
"learning_rate": 5.7748793514678394e-05,
|
| 336 |
+
"loss": 0.7664,
|
| 337 |
+
"num_input_tokens_seen": 2744502,
|
| 338 |
+
"step": 200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7701564380264742,
|
| 342 |
+
"eval_loss": 0.6271176338195801,
|
| 343 |
+
"eval_runtime": 6.1565,
|
| 344 |
+
"eval_samples_per_second": 24.365,
|
| 345 |
+
"eval_steps_per_second": 12.182,
|
| 346 |
+
"num_input_tokens_seen": 2744502,
|
| 347 |
+
"step": 200
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.789410348977136,
|
| 351 |
+
"grad_norm": 0.5261389017105103,
|
| 352 |
+
"learning_rate": 5.6595476559840604e-05,
|
| 353 |
+
"loss": 0.7619,
|
| 354 |
+
"num_input_tokens_seen": 2806924,
|
| 355 |
+
"step": 205
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.8086642599277978,
|
| 359 |
+
"grad_norm": 0.6377142667770386,
|
| 360 |
+
"learning_rate": 5.542524497952544e-05,
|
| 361 |
+
"loss": 0.7611,
|
| 362 |
+
"num_input_tokens_seen": 2880096,
|
| 363 |
+
"step": 210
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.8279181708784596,
|
| 367 |
+
"grad_norm": 0.6118225455284119,
|
| 368 |
+
"learning_rate": 5.4239291510128936e-05,
|
| 369 |
+
"loss": 0.7704,
|
| 370 |
+
"num_input_tokens_seen": 2953254,
|
| 371 |
+
"step": 215
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.8471720818291215,
|
| 375 |
+
"grad_norm": 0.623435378074646,
|
| 376 |
+
"learning_rate": 5.3038824912285144e-05,
|
| 377 |
+
"loss": 0.759,
|
| 378 |
+
"num_input_tokens_seen": 3018146,
|
| 379 |
+
"step": 220
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.8664259927797834,
|
| 383 |
+
"grad_norm": 0.7073508501052856,
|
| 384 |
+
"learning_rate": 5.182506873885964e-05,
|
| 385 |
+
"loss": 0.7612,
|
| 386 |
+
"num_input_tokens_seen": 3085348,
|
| 387 |
+
"step": 225
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.8856799037304453,
|
| 391 |
+
"grad_norm": 0.6435876488685608,
|
| 392 |
+
"learning_rate": 5.059926008786648e-05,
|
| 393 |
+
"loss": 0.7582,
|
| 394 |
+
"num_input_tokens_seen": 3155840,
|
| 395 |
+
"step": 230
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.9049338146811071,
|
| 399 |
+
"grad_norm": 0.7241389751434326,
|
| 400 |
+
"learning_rate": 4.93626483415794e-05,
|
| 401 |
+
"loss": 0.7502,
|
| 402 |
+
"num_input_tokens_seen": 3228332,
|
| 403 |
+
"step": 235
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.924187725631769,
|
| 407 |
+
"grad_norm": 0.583131730556488,
|
| 408 |
+
"learning_rate": 4.811649389312267e-05,
|
| 409 |
+
"loss": 0.7573,
|
| 410 |
+
"num_input_tokens_seen": 3292876,
|
| 411 |
+
"step": 240
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.9434416365824309,
|
| 415 |
+
"grad_norm": 0.5829302072525024,
|
| 416 |
+
"learning_rate": 4.686206686183914e-05,
|
| 417 |
+
"loss": 0.7535,
|
| 418 |
+
"num_input_tokens_seen": 3356266,
|
| 419 |
+
"step": 245
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.9626955475330926,
|
| 423 |
+
"grad_norm": 0.6448350548744202,
|
| 424 |
+
"learning_rate": 4.560064579874517e-05,
|
| 425 |
+
"loss": 0.738,
|
| 426 |
+
"num_input_tokens_seen": 3436068,
|
| 427 |
+
"step": 250
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.9819494584837545,
|
| 431 |
+
"grad_norm": 0.5773698687553406,
|
| 432 |
+
"learning_rate": 4.433351638339173e-05,
|
| 433 |
+
"loss": 0.7597,
|
| 434 |
+
"num_input_tokens_seen": 3507054,
|
| 435 |
+
"step": 255
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.0012033694344165,
|
| 439 |
+
"grad_norm": 0.6720272302627563,
|
| 440 |
+
"learning_rate": 4.306197011345984e-05,
|
| 441 |
+
"loss": 0.766,
|
| 442 |
+
"num_input_tokens_seen": 3578891,
|
| 443 |
+
"step": 260
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0204572803850782,
|
| 447 |
+
"grad_norm": 0.594204306602478,
|
| 448 |
+
"learning_rate": 4.178730298842592e-05,
|
| 449 |
+
"loss": 0.6578,
|
| 450 |
+
"num_input_tokens_seen": 3657955,
|
| 451 |
+
"step": 265
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.03971119133574,
|
| 455 |
+
"grad_norm": 0.5978640913963318,
|
| 456 |
+
"learning_rate": 4.051081418863896e-05,
|
| 457 |
+
"loss": 0.6649,
|
| 458 |
+
"num_input_tokens_seen": 3726843,
|
| 459 |
+
"step": 270
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.058965102286402,
|
| 463 |
+
"grad_norm": 0.6276839971542358,
|
| 464 |
+
"learning_rate": 3.923380475115544e-05,
|
| 465 |
+
"loss": 0.6792,
|
| 466 |
+
"num_input_tokens_seen": 3790497,
|
| 467 |
+
"step": 275
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.0782190132370637,
|
| 471 |
+
"grad_norm": 0.6850570440292358,
|
| 472 |
+
"learning_rate": 3.7957576243681985e-05,
|
| 473 |
+
"loss": 0.6622,
|
| 474 |
+
"num_input_tokens_seen": 3865393,
|
| 475 |
+
"step": 280
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.0974729241877257,
|
| 479 |
+
"grad_norm": 0.5756229162216187,
|
| 480 |
+
"learning_rate": 3.668342943797706e-05,
|
| 481 |
+
"loss": 0.6531,
|
| 482 |
+
"num_input_tokens_seen": 3932181,
|
| 483 |
+
"step": 285
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.1167268351383874,
|
| 487 |
+
"grad_norm": 0.6151105761528015,
|
| 488 |
+
"learning_rate": 3.541266298406399e-05,
|
| 489 |
+
"loss": 0.673,
|
| 490 |
+
"num_input_tokens_seen": 4005021,
|
| 491 |
+
"step": 290
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.1359807460890494,
|
| 495 |
+
"grad_norm": 0.6357588171958923,
|
| 496 |
+
"learning_rate": 3.4146572086606516e-05,
|
| 497 |
+
"loss": 0.6616,
|
| 498 |
+
"num_input_tokens_seen": 4068541,
|
| 499 |
+
"step": 295
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.1552346570397112,
|
| 503 |
+
"grad_norm": 0.6211041212081909,
|
| 504 |
+
"learning_rate": 3.288644718479594e-05,
|
| 505 |
+
"loss": 0.6584,
|
| 506 |
+
"num_input_tokens_seen": 4137699,
|
| 507 |
+
"step": 300
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.1552346570397112,
|
| 511 |
+
"eval_loss": 0.6145883202552795,
|
| 512 |
+
"eval_runtime": 6.1807,
|
| 513 |
+
"eval_samples_per_second": 24.269,
|
| 514 |
+
"eval_steps_per_second": 12.134,
|
| 515 |
+
"num_input_tokens_seen": 4137699,
|
| 516 |
+
"step": 300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.1744885679903732,
|
| 520 |
+
"grad_norm": 0.6347965598106384,
|
| 521 |
+
"learning_rate": 3.163357263709534e-05,
|
| 522 |
+
"loss": 0.6388,
|
| 523 |
+
"num_input_tokens_seen": 4206939,
|
| 524 |
+
"step": 305
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.193742478941035,
|
| 528 |
+
"grad_norm": 0.6002417802810669,
|
| 529 |
+
"learning_rate": 3.0389225412181572e-05,
|
| 530 |
+
"loss": 0.6841,
|
| 531 |
+
"num_input_tokens_seen": 4271739,
|
| 532 |
+
"step": 310
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.2129963898916967,
|
| 536 |
+
"grad_norm": 0.5483217239379883,
|
| 537 |
+
"learning_rate": 2.9154673787419124e-05,
|
| 538 |
+
"loss": 0.6681,
|
| 539 |
+
"num_input_tokens_seen": 4339421,
|
| 540 |
+
"step": 315
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.2322503008423586,
|
| 544 |
+
"grad_norm": 0.6174812912940979,
|
| 545 |
+
"learning_rate": 2.793117605619231e-05,
|
| 546 |
+
"loss": 0.6713,
|
| 547 |
+
"num_input_tokens_seen": 4398549,
|
| 548 |
+
"step": 320
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.2515042117930204,
|
| 552 |
+
"grad_norm": 0.6561586856842041,
|
| 553 |
+
"learning_rate": 2.6719979245413676e-05,
|
| 554 |
+
"loss": 0.6682,
|
| 555 |
+
"num_input_tokens_seen": 4467901,
|
| 556 |
+
"step": 325
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.2707581227436824,
|
| 560 |
+
"grad_norm": 0.617612361907959,
|
| 561 |
+
"learning_rate": 2.552231784451528e-05,
|
| 562 |
+
"loss": 0.6643,
|
| 563 |
+
"num_input_tokens_seen": 4525255,
|
| 564 |
+
"step": 330
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.2900120336943441,
|
| 568 |
+
"grad_norm": 0.6367979645729065,
|
| 569 |
+
"learning_rate": 2.4339412547218845e-05,
|
| 570 |
+
"loss": 0.6444,
|
| 571 |
+
"num_input_tokens_seen": 4597459,
|
| 572 |
+
"step": 335
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.3092659446450061,
|
| 576 |
+
"grad_norm": 0.5901610851287842,
|
| 577 |
+
"learning_rate": 2.3172469007366636e-05,
|
| 578 |
+
"loss": 0.6432,
|
| 579 |
+
"num_input_tokens_seen": 4678093,
|
| 580 |
+
"step": 340
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.3285198555956679,
|
| 584 |
+
"grad_norm": 0.6240355968475342,
|
| 585 |
+
"learning_rate": 2.20226766100817e-05,
|
| 586 |
+
"loss": 0.6558,
|
| 587 |
+
"num_input_tokens_seen": 4750971,
|
| 588 |
+
"step": 345
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.3477737665463296,
|
| 592 |
+
"grad_norm": 0.612914502620697,
|
| 593 |
+
"learning_rate": 2.089120725950948e-05,
|
| 594 |
+
"loss": 0.6506,
|
| 595 |
+
"num_input_tokens_seen": 4826861,
|
| 596 |
+
"step": 350
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.3670276774969916,
|
| 600 |
+
"grad_norm": 0.6090959906578064,
|
| 601 |
+
"learning_rate": 1.9779214184376857e-05,
|
| 602 |
+
"loss": 0.6545,
|
| 603 |
+
"num_input_tokens_seen": 4895159,
|
| 604 |
+
"step": 355
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.3862815884476534,
|
| 608 |
+
"grad_norm": 0.5601783990859985,
|
| 609 |
+
"learning_rate": 1.8687830762585378e-05,
|
| 610 |
+
"loss": 0.6535,
|
| 611 |
+
"num_input_tokens_seen": 4966107,
|
| 612 |
+
"step": 360
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.4055354993983153,
|
| 616 |
+
"grad_norm": 0.5911448001861572,
|
| 617 |
+
"learning_rate": 1.761816936603744e-05,
|
| 618 |
+
"loss": 0.6497,
|
| 619 |
+
"num_input_tokens_seen": 5031601,
|
| 620 |
+
"step": 365
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.424789410348977,
|
| 624 |
+
"grad_norm": 0.6376362442970276,
|
| 625 |
+
"learning_rate": 1.6571320226872208e-05,
|
| 626 |
+
"loss": 0.6616,
|
| 627 |
+
"num_input_tokens_seen": 5100787,
|
| 628 |
+
"step": 370
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.444043321299639,
|
| 632 |
+
"grad_norm": 0.5783751010894775,
|
| 633 |
+
"learning_rate": 1.5548350326267135e-05,
|
| 634 |
+
"loss": 0.6604,
|
| 635 |
+
"num_input_tokens_seen": 5173727,
|
| 636 |
+
"step": 375
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.4632972322503008,
|
| 640 |
+
"grad_norm": 0.5625059604644775,
|
| 641 |
+
"learning_rate": 1.4550302306937619e-05,
|
| 642 |
+
"loss": 0.6389,
|
| 643 |
+
"num_input_tokens_seen": 5245681,
|
| 644 |
+
"step": 380
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.4825511432009626,
|
| 648 |
+
"grad_norm": 0.6026486158370972,
|
| 649 |
+
"learning_rate": 1.3578193410443068e-05,
|
| 650 |
+
"loss": 0.6506,
|
| 651 |
+
"num_input_tokens_seen": 5324203,
|
| 652 |
+
"step": 385
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.5018050541516246,
|
| 656 |
+
"grad_norm": 0.7199910879135132,
|
| 657 |
+
"learning_rate": 1.263301444038279e-05,
|
| 658 |
+
"loss": 0.656,
|
| 659 |
+
"num_input_tokens_seen": 5388385,
|
| 660 |
+
"step": 390
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.5210589651022866,
|
| 664 |
+
"grad_norm": 0.6065146327018738,
|
| 665 |
+
"learning_rate": 1.1715728752538103e-05,
|
| 666 |
+
"loss": 0.6634,
|
| 667 |
+
"num_input_tokens_seen": 5455431,
|
| 668 |
+
"step": 395
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.5403128760529483,
|
| 672 |
+
"grad_norm": 0.6021776795387268,
|
| 673 |
+
"learning_rate": 1.0827271272990206e-05,
|
| 674 |
+
"loss": 0.6348,
|
| 675 |
+
"num_input_tokens_seen": 5518719,
|
| 676 |
+
"step": 400
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.5403128760529483,
|
| 680 |
+
"eval_loss": 0.6049174070358276,
|
| 681 |
+
"eval_runtime": 6.1672,
|
| 682 |
+
"eval_samples_per_second": 24.322,
|
| 683 |
+
"eval_steps_per_second": 12.161,
|
| 684 |
+
"num_input_tokens_seen": 5518719,
|
| 685 |
+
"step": 400
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.55956678700361,
|
| 689 |
+
"grad_norm": 0.5880686044692993,
|
| 690 |
+
"learning_rate": 9.968547545214444e-06,
|
| 691 |
+
"loss": 0.6604,
|
| 692 |
+
"num_input_tokens_seen": 5592171,
|
| 693 |
+
"step": 405
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.578820697954272,
|
| 697 |
+
"grad_norm": 0.611405611038208,
|
| 698 |
+
"learning_rate": 9.140432807122282e-06,
|
| 699 |
+
"loss": 0.6806,
|
| 700 |
+
"num_input_tokens_seen": 5661159,
|
| 701 |
+
"step": 410
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 1.5980746089049338,
|
| 705 |
+
"grad_norm": 0.5994818806648254,
|
| 706 |
+
"learning_rate": 8.343771098991604e-06,
|
| 707 |
+
"loss": 0.6492,
|
| 708 |
+
"num_input_tokens_seen": 5721247,
|
| 709 |
+
"step": 415
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.6173285198555956,
|
| 713 |
+
"grad_norm": 0.6033297181129456,
|
| 714 |
+
"learning_rate": 7.57937440319462e-06,
|
| 715 |
+
"loss": 0.6808,
|
| 716 |
+
"num_input_tokens_seen": 5792521,
|
| 717 |
+
"step": 420
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.6365824308062575,
|
| 721 |
+
"grad_norm": 0.6016368269920349,
|
| 722 |
+
"learning_rate": 6.848021816600221e-06,
|
| 723 |
+
"loss": 0.6533,
|
| 724 |
+
"num_input_tokens_seen": 5864477,
|
| 725 |
+
"step": 425
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.6558363417569195,
|
| 729 |
+
"grad_norm": 0.6104902625083923,
|
| 730 |
+
"learning_rate": 6.15045875649424e-06,
|
| 731 |
+
"loss": 0.6342,
|
| 732 |
+
"num_input_tokens_seen": 5926641,
|
| 733 |
+
"step": 430
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.6750902527075813,
|
| 737 |
+
"grad_norm": 0.6614465713500977,
|
| 738 |
+
"learning_rate": 5.487396200826957e-06,
|
| 739 |
+
"loss": 0.6598,
|
| 740 |
+
"num_input_tokens_seen": 5996769,
|
| 741 |
+
"step": 435
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.694344163658243,
|
| 745 |
+
"grad_norm": 0.6114799380302429,
|
| 746 |
+
"learning_rate": 4.859509963562313e-06,
|
| 747 |
+
"loss": 0.6635,
|
| 748 |
+
"num_input_tokens_seen": 6066617,
|
| 749 |
+
"step": 440
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.713598074608905,
|
| 753 |
+
"grad_norm": 0.5675967335700989,
|
| 754 |
+
"learning_rate": 4.267440005867252e-06,
|
| 755 |
+
"loss": 0.6733,
|
| 756 |
+
"num_input_tokens_seen": 6132661,
|
| 757 |
+
"step": 445
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.7328519855595668,
|
| 761 |
+
"grad_norm": 0.5562564134597778,
|
| 762 |
+
"learning_rate": 3.7117897838435225e-06,
|
| 763 |
+
"loss": 0.6298,
|
| 764 |
+
"num_input_tokens_seen": 6201793,
|
| 765 |
+
"step": 450
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.7521058965102285,
|
| 769 |
+
"grad_norm": 0.607563316822052,
|
| 770 |
+
"learning_rate": 3.19312563346633e-06,
|
| 771 |
+
"loss": 0.6473,
|
| 772 |
+
"num_input_tokens_seen": 6270295,
|
| 773 |
+
"step": 455
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.7713598074608905,
|
| 777 |
+
"grad_norm": 0.5713885426521301,
|
| 778 |
+
"learning_rate": 2.7119761933572132e-06,
|
| 779 |
+
"loss": 0.6682,
|
| 780 |
+
"num_input_tokens_seen": 6345853,
|
| 781 |
+
"step": 460
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.7906137184115525,
|
| 785 |
+
"grad_norm": 0.6208235621452332,
|
| 786 |
+
"learning_rate": 2.268831865979073e-06,
|
| 787 |
+
"loss": 0.6354,
|
| 788 |
+
"num_input_tokens_seen": 6410491,
|
| 789 |
+
"step": 465
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.8098676293622142,
|
| 793 |
+
"grad_norm": 0.6321476101875305,
|
| 794 |
+
"learning_rate": 1.8641443178027784e-06,
|
| 795 |
+
"loss": 0.6501,
|
| 796 |
+
"num_input_tokens_seen": 6476011,
|
| 797 |
+
"step": 470
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.829121540312876,
|
| 801 |
+
"grad_norm": 0.671848475933075,
|
| 802 |
+
"learning_rate": 1.4983260189546322e-06,
|
| 803 |
+
"loss": 0.6699,
|
| 804 |
+
"num_input_tokens_seen": 6548557,
|
| 805 |
+
"step": 475
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.848375451263538,
|
| 809 |
+
"grad_norm": 0.6751930713653564,
|
| 810 |
+
"learning_rate": 1.1717498228140146e-06,
|
| 811 |
+
"loss": 0.6615,
|
| 812 |
+
"num_input_tokens_seen": 6623485,
|
| 813 |
+
"step": 480
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.8676293622141997,
|
| 817 |
+
"grad_norm": 0.6214536428451538,
|
| 818 |
+
"learning_rate": 8.847485859896365e-07,
|
| 819 |
+
"loss": 0.6627,
|
| 820 |
+
"num_input_tokens_seen": 6689943,
|
| 821 |
+
"step": 485
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.8868832731648615,
|
| 825 |
+
"grad_norm": 0.5981723070144653,
|
| 826 |
+
"learning_rate": 6.376148290617146e-07,
|
| 827 |
+
"loss": 0.6549,
|
| 828 |
+
"num_input_tokens_seen": 6757657,
|
| 829 |
+
"step": 490
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.9061371841155235,
|
| 833 |
+
"grad_norm": 0.5489323139190674,
|
| 834 |
+
"learning_rate": 4.306004384359419e-07,
|
| 835 |
+
"loss": 0.6755,
|
| 836 |
+
"num_input_tokens_seen": 6824219,
|
| 837 |
+
"step": 495
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.9253910950661854,
|
| 841 |
+
"grad_norm": 0.5502476096153259,
|
| 842 |
+
"learning_rate": 2.639164096129987e-07,
|
| 843 |
+
"loss": 0.6372,
|
| 844 |
+
"num_input_tokens_seen": 6895203,
|
| 845 |
+
"step": 500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.9253910950661854,
|
| 849 |
+
"eval_loss": 0.6038384437561035,
|
| 850 |
+
"eval_runtime": 6.1961,
|
| 851 |
+
"eval_samples_per_second": 24.209,
|
| 852 |
+
"eval_steps_per_second": 12.104,
|
| 853 |
+
"num_input_tokens_seen": 6895203,
|
| 854 |
+
"step": 500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.9446450060168472,
|
| 858 |
+
"grad_norm": 0.7226577997207642,
|
| 859 |
+
"learning_rate": 1.3773263213540332e-07,
|
| 860 |
+
"loss": 0.6492,
|
| 861 |
+
"num_input_tokens_seen": 6971035,
|
| 862 |
+
"step": 505
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.963898916967509,
|
| 866 |
+
"grad_norm": 0.5310623049736023,
|
| 867 |
+
"learning_rate": 5.2177716430801276e-08,
|
| 868 |
+
"loss": 0.6521,
|
| 869 |
+
"num_input_tokens_seen": 7041317,
|
| 870 |
+
"step": 510
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.983152827918171,
|
| 874 |
+
"grad_norm": 0.5827205777168274,
|
| 875 |
+
"learning_rate": 7.338862728225593e-09,
|
| 876 |
+
"loss": 0.6646,
|
| 877 |
+
"num_input_tokens_seen": 7098531,
|
| 878 |
+
"step": 515
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.994705174488568,
|
| 882 |
+
"num_input_tokens_seen": 7138765,
|
| 883 |
+
"step": 518,
|
| 884 |
+
"total_flos": 1.1924408841596928e+17,
|
| 885 |
+
"train_loss": 0.744573145759612,
|
| 886 |
+
"train_runtime": 5797.4674,
|
| 887 |
+
"train_samples_per_second": 5.733,
|
| 888 |
+
"train_steps_per_second": 0.089
|
| 889 |
+
}
|
| 890 |
+
],
|
| 891 |
+
"logging_steps": 5,
|
| 892 |
+
"max_steps": 518,
|
| 893 |
+
"num_input_tokens_seen": 7138765,
|
| 894 |
+
"num_train_epochs": 2,
|
| 895 |
+
"save_steps": 100,
|
| 896 |
+
"stateful_callbacks": {
|
| 897 |
+
"TrainerControl": {
|
| 898 |
+
"args": {
|
| 899 |
+
"should_epoch_stop": false,
|
| 900 |
+
"should_evaluate": false,
|
| 901 |
+
"should_log": false,
|
| 902 |
+
"should_save": true,
|
| 903 |
+
"should_training_stop": true
|
| 904 |
+
},
|
| 905 |
+
"attributes": {}
|
| 906 |
+
}
|
| 907 |
+
},
|
| 908 |
+
"total_flos": 1.1924408841596928e+17,
|
| 909 |
+
"train_batch_size": 2,
|
| 910 |
+
"trial_name": null,
|
| 911 |
+
"trial_params": null
|
| 912 |
+
}
|