Upload folder using huggingface_hub
Browse files- README.md +14 -55
- checkpoint-13992/config.json +28 -0
- checkpoint-13992/model.safetensors +3 -0
- checkpoint-13992/optimizer.pt +3 -0
- checkpoint-13992/rng_state.pth +3 -0
- checkpoint-13992/scaler.pt +3 -0
- checkpoint-13992/scheduler.pt +3 -0
- checkpoint-13992/trainer_state.json +1095 -0
- checkpoint-13992/training_args.bin +3 -0
- checkpoint-15273/config.json +28 -0
- checkpoint-15273/model.safetensors +3 -0
- checkpoint-15273/optimizer.pt +3 -0
- checkpoint-15273/rng_state.pth +3 -0
- checkpoint-15273/scaler.pt +3 -0
- checkpoint-15273/scheduler.pt +3 -0
- checkpoint-15273/trainer_state.json +1194 -0
- checkpoint-15273/training_args.bin +3 -0
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -11,7 +11,14 @@ tags:
|
|
| 11 |
|
| 12 |
# Sindhi-BERT-base
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
## Model Details
|
| 17 |
|
|
@@ -19,62 +26,14 @@ The first BERT-style language model trained from scratch on Sindhi text, using a
|
|
| 19 |
|---|---|
|
| 20 |
| Architecture | RoBERTa-base |
|
| 21 |
| Vocabulary | 32,000 tokens (pure Sindhi BPE) |
|
| 22 |
-
| Hidden size | 768 |
|
| 23 |
-
| Layers | 12 |
|
| 24 |
-
| Attention heads | 12 |
|
| 25 |
-
| Max length | 512 tokens |
|
| 26 |
| Parameters | ~125M |
|
| 27 |
| Language | Sindhi (sd) |
|
| 28 |
| License | MIT |
|
| 29 |
|
| 30 |
-
##
|
| 31 |
-
|
| 32 |
-
| Detail | Value |
|
| 33 |
-
|---|---|
|
| 34 |
-
| Training data | 500K Sindhi sentences |
|
| 35 |
-
| Full corpus size | 447 MB clean Sindhi text |
|
| 36 |
-
| Epochs | 5 |
|
| 37 |
-
| Batch size | 256 (effective) |
|
| 38 |
-
| Learning rate | 1e-4 |
|
| 39 |
-
| Hardware | A100 GPU |
|
| 40 |
-
| Training time | 301.7 minutes |
|
| 41 |
-
| Final eval loss | 4.358 |
|
| 42 |
-
| Final perplexity | 78.10 |
|
| 43 |
-
|
| 44 |
-
## Tokenizer
|
| 45 |
-
|
| 46 |
-
Trained a custom Sindhi BPE tokenizer with 32,000 vocabulary size built specifically for Sindhi script. Every token is a real Sindhi word or subword — unlike multilingual models like mBERT or XLM-R which give Sindhi very limited vocabulary coverage.
|
| 47 |
-
|
| 48 |
-
Each Sindhi word stays as ONE whole token:
|
| 49 |
-
|
| 50 |
-
Input : سنڌي ٻولي دنيا جي قديم ٻولين مان هڪ آهي
|
| 51 |
-
|
| 52 |
-
Tokens : ['سنڌي', 'ٻولي', 'دنيا', 'جي', 'قديم', 'ٻولين', 'مان', 'هڪ', 'آهي']
|
| 53 |
-
|
| 54 |
-
Count : 9 words = 9 tokens
|
| 55 |
-
|
| 56 |
-
## Fill-Mask Results
|
| 57 |
-
|
| 58 |
-
Tested on 10 Sindhi sentences after 5 epochs of training:
|
| 59 |
-
|
| 60 |
-
| Input | Top Prediction | Score | Quality |
|
| 61 |
-
|---|---|---|---|
|
| 62 |
-
| سنڌي ___ دنيا جي قديم ٻولين | ٻولي (language) | 15.47% | Perfect |
|
| 63 |
-
| شاهه لطيف سنڌي ___ جو وڏو شاعر | ادب (literature) | 16.48% | Perfect |
|
| 64 |
-
| استاد شاگردن کي ___ سيکاري | تعليم (education) | 5.58% | Perfect |
|
| 65 |
-
| دنيا ___ گھڻي مصروف آھي | ۾ (in) | 27.98% | Correct |
|
| 66 |
-
| سنڌ جي ___ ڏاڍي پراڻي آهي | تاريخ (history) | Top 2 | Good |
|
| 67 |
-
| ڪراچي سنڌ جو سڀ کان وڏو ___ آهي | شهر (city) | Top 3 | Close |
|
| 68 |
-
| ٻار ___ ۾ پڙهن ٿا | گهر (home) | Top 2 | Close |
|
| 69 |
-
|
| 70 |
-
Overall: 50% top-1 accuracy after 5 epochs on 500K sentences.
|
| 71 |
-
Results improve significantly with more training.
|
| 72 |
-
|
| 73 |
-
## Citation
|
| 74 |
-
|
| 75 |
-
If you use this model please cite:
|
| 76 |
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
|
|
|
|
|
| 11 |
|
| 12 |
# Sindhi-BERT-base
|
| 13 |
|
| 14 |
+
BERT-style model trained from scratch on Sindhi text.
|
| 15 |
+
|
| 16 |
+
## Training History
|
| 17 |
+
|
| 18 |
+
| Session | Data | Epochs | Perplexity |
|
| 19 |
+
|---|---|---|---|
|
| 20 |
+
| Session 1 | 500K lines | 5 | 78.10 |
|
| 21 |
+
| Session 2 | 2.1M lines | 3 | 41.62 |
|
| 22 |
|
| 23 |
## Model Details
|
| 24 |
|
|
|
|
| 26 |
|---|---|
|
| 27 |
| Architecture | RoBERTa-base |
|
| 28 |
| Vocabulary | 32,000 tokens (pure Sindhi BPE) |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
| Parameters | ~125M |
|
| 30 |
| Language | Sindhi (sd) |
|
| 31 |
| License | MIT |
|
| 32 |
|
| 33 |
+
## Roadmap
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
+
- [x] Session 1 — 500K lines, 5 epochs
|
| 36 |
+
- [x] Session 2 — 2.1M lines, 3 more epochs
|
| 37 |
+
- [ ] Session 3 — more epochs
|
| 38 |
+
- [ ] Spell checker fine-tuning
|
| 39 |
+
- [ ] Next word prediction
|
checkpoint-13992/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "roberta",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"transformers_version": "5.0.0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 32001
|
| 28 |
+
}
|
checkpoint-13992/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f30d3263e4f5945a574c395e67860f77b1c2ad46656375ee05131edc7f9af6e
|
| 3 |
+
size 442633860
|
checkpoint-13992/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:317967ab747cc0af5476a61cd478cf7c0a8ebae90d31f4849479a9fb3cf1b04d
|
| 3 |
+
size 885391563
|
checkpoint-13992/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d211a47b4b3b335c468d44ed76f120d5089780b4eb88aa346a57b160dd0dda15
|
| 3 |
+
size 14645
|
checkpoint-13992/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ecd99389d0b0fa98b257c145b8eae39d68db39de8045d8bf547a8b89832a7a5
|
| 3 |
+
size 1383
|
checkpoint-13992/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47503d0942a02a8bf8bef3e54b3e92aca8d6588333c6748da7af2330423c43ae
|
| 3 |
+
size 1465
|
checkpoint-13992/trainer_state.json
ADDED
|
@@ -0,0 +1,1095 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 13992,
|
| 3 |
+
"best_metric": 3.7217817306518555,
|
| 4 |
+
"best_model_checkpoint": "sindhibert_session2/checkpoint-13992",
|
| 5 |
+
"epoch": 2.748397868735728,
|
| 6 |
+
"eval_steps": 1272,
|
| 7 |
+
"global_step": 13992,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.019642988680727773,
|
| 14 |
+
"grad_norm": 16.122173309326172,
|
| 15 |
+
"learning_rate": 9.900000000000002e-06,
|
| 16 |
+
"loss": 36.5051904296875,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.039285977361455546,
|
| 21 |
+
"grad_norm": 18.11626434326172,
|
| 22 |
+
"learning_rate": 1.9900000000000003e-05,
|
| 23 |
+
"loss": 36.368505859375,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05892896604218332,
|
| 28 |
+
"grad_norm": 18.927509307861328,
|
| 29 |
+
"learning_rate": 2.9900000000000002e-05,
|
| 30 |
+
"loss": 36.45832275390625,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07857195472291109,
|
| 35 |
+
"grad_norm": 18.480167388916016,
|
| 36 |
+
"learning_rate": 3.99e-05,
|
| 37 |
+
"loss": 36.31460693359375,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09821494340363886,
|
| 42 |
+
"grad_norm": 19.010652542114258,
|
| 43 |
+
"learning_rate": 4.99e-05,
|
| 44 |
+
"loss": 36.24136962890625,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11785793208436664,
|
| 49 |
+
"grad_norm": 19.11362075805664,
|
| 50 |
+
"learning_rate": 4.966492926284438e-05,
|
| 51 |
+
"loss": 36.54402587890625,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1375009207650944,
|
| 56 |
+
"grad_norm": 19.41926383972168,
|
| 57 |
+
"learning_rate": 4.93264739727882e-05,
|
| 58 |
+
"loss": 36.28423095703125,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15714390944582218,
|
| 63 |
+
"grad_norm": 20.20358657836914,
|
| 64 |
+
"learning_rate": 4.898801868273201e-05,
|
| 65 |
+
"loss": 36.2180615234375,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.17678689812654996,
|
| 70 |
+
"grad_norm": 18.598957061767578,
|
| 71 |
+
"learning_rate": 4.864956339267583e-05,
|
| 72 |
+
"loss": 36.1883984375,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.19642988680727771,
|
| 77 |
+
"grad_norm": 18.320087432861328,
|
| 78 |
+
"learning_rate": 4.831110810261965e-05,
|
| 79 |
+
"loss": 36.0933837890625,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2160728754880055,
|
| 84 |
+
"grad_norm": 21.353364944458008,
|
| 85 |
+
"learning_rate": 4.797265281256346e-05,
|
| 86 |
+
"loss": 35.95175048828125,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.23571586416873327,
|
| 91 |
+
"grad_norm": 19.709365844726562,
|
| 92 |
+
"learning_rate": 4.763419752250728e-05,
|
| 93 |
+
"loss": 35.99169921875,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.24985881601885726,
|
| 98 |
+
"eval_loss": 4.386976718902588,
|
| 99 |
+
"eval_runtime": 41.9212,
|
| 100 |
+
"eval_samples_per_second": 477.086,
|
| 101 |
+
"eval_steps_per_second": 14.909,
|
| 102 |
+
"step": 1272
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.255358852849461,
|
| 106 |
+
"grad_norm": 17.78667449951172,
|
| 107 |
+
"learning_rate": 4.729574223245109e-05,
|
| 108 |
+
"loss": 35.86061279296875,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2750018415301888,
|
| 113 |
+
"grad_norm": 21.036474227905273,
|
| 114 |
+
"learning_rate": 4.695728694239491e-05,
|
| 115 |
+
"loss": 35.78255859375,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2946448302109166,
|
| 120 |
+
"grad_norm": 19.002052307128906,
|
| 121 |
+
"learning_rate": 4.661883165233873e-05,
|
| 122 |
+
"loss": 35.5993408203125,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.31428781889164437,
|
| 127 |
+
"grad_norm": 19.828800201416016,
|
| 128 |
+
"learning_rate": 4.6280376362282543e-05,
|
| 129 |
+
"loss": 35.70918701171875,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.33393080757237215,
|
| 134 |
+
"grad_norm": 17.12042236328125,
|
| 135 |
+
"learning_rate": 4.594192107222636e-05,
|
| 136 |
+
"loss": 35.58583251953125,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3535737962530999,
|
| 141 |
+
"grad_norm": 19.869712829589844,
|
| 142 |
+
"learning_rate": 4.560346578217018e-05,
|
| 143 |
+
"loss": 35.3600537109375,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3732167849338277,
|
| 148 |
+
"grad_norm": 18.914470672607422,
|
| 149 |
+
"learning_rate": 4.5265010492113994e-05,
|
| 150 |
+
"loss": 35.34132080078125,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.39285977361455543,
|
| 155 |
+
"grad_norm": 18.888940811157227,
|
| 156 |
+
"learning_rate": 4.4926555202057814e-05,
|
| 157 |
+
"loss": 35.33590576171875,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.4125027622952832,
|
| 162 |
+
"grad_norm": 20.27227783203125,
|
| 163 |
+
"learning_rate": 4.4588099912001626e-05,
|
| 164 |
+
"loss": 35.22805908203125,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.432145750976011,
|
| 169 |
+
"grad_norm": 15.550501823425293,
|
| 170 |
+
"learning_rate": 4.424964462194544e-05,
|
| 171 |
+
"loss": 35.256953125,
|
| 172 |
+
"step": 2200
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.45178873965673877,
|
| 176 |
+
"grad_norm": 17.671451568603516,
|
| 177 |
+
"learning_rate": 4.391118933188926e-05,
|
| 178 |
+
"loss": 35.056826171875,
|
| 179 |
+
"step": 2300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.47143172833746655,
|
| 183 |
+
"grad_norm": 18.74838638305664,
|
| 184 |
+
"learning_rate": 4.357273404183308e-05,
|
| 185 |
+
"loss": 34.9271826171875,
|
| 186 |
+
"step": 2400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.49107471701819433,
|
| 190 |
+
"grad_norm": 20.912931442260742,
|
| 191 |
+
"learning_rate": 4.323427875177689e-05,
|
| 192 |
+
"loss": 34.793916015625,
|
| 193 |
+
"step": 2500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.4997176320377145,
|
| 197 |
+
"eval_loss": 4.270185947418213,
|
| 198 |
+
"eval_runtime": 41.8695,
|
| 199 |
+
"eval_samples_per_second": 477.675,
|
| 200 |
+
"eval_steps_per_second": 14.927,
|
| 201 |
+
"step": 2544
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.510717705698922,
|
| 205 |
+
"grad_norm": 18.11321258544922,
|
| 206 |
+
"learning_rate": 4.289582346172071e-05,
|
| 207 |
+
"loss": 34.97314453125,
|
| 208 |
+
"step": 2600
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.5303606943796498,
|
| 212 |
+
"grad_norm": 19.38896942138672,
|
| 213 |
+
"learning_rate": 4.255736817166453e-05,
|
| 214 |
+
"loss": 34.873974609375,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5500036830603776,
|
| 219 |
+
"grad_norm": 19.479278564453125,
|
| 220 |
+
"learning_rate": 4.221891288160834e-05,
|
| 221 |
+
"loss": 34.713251953125,
|
| 222 |
+
"step": 2800
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5696466717411054,
|
| 226 |
+
"grad_norm": 19.849210739135742,
|
| 227 |
+
"learning_rate": 4.188045759155216e-05,
|
| 228 |
+
"loss": 34.66454833984375,
|
| 229 |
+
"step": 2900
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5892896604218332,
|
| 233 |
+
"grad_norm": 19.59630012512207,
|
| 234 |
+
"learning_rate": 4.154200230149597e-05,
|
| 235 |
+
"loss": 34.546259765625,
|
| 236 |
+
"step": 3000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.608932649102561,
|
| 240 |
+
"grad_norm": 18.32138442993164,
|
| 241 |
+
"learning_rate": 4.120354701143979e-05,
|
| 242 |
+
"loss": 34.460576171875,
|
| 243 |
+
"step": 3100
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.6285756377832887,
|
| 247 |
+
"grad_norm": 17.825464248657227,
|
| 248 |
+
"learning_rate": 4.086509172138361e-05,
|
| 249 |
+
"loss": 34.3186962890625,
|
| 250 |
+
"step": 3200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.6482186264640165,
|
| 254 |
+
"grad_norm": 19.180105209350586,
|
| 255 |
+
"learning_rate": 4.052663643132742e-05,
|
| 256 |
+
"loss": 34.40132080078125,
|
| 257 |
+
"step": 3300
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.6678616151447443,
|
| 261 |
+
"grad_norm": 18.498641967773438,
|
| 262 |
+
"learning_rate": 4.018818114127124e-05,
|
| 263 |
+
"loss": 34.2248828125,
|
| 264 |
+
"step": 3400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.6875046038254721,
|
| 268 |
+
"grad_norm": 19.08323097229004,
|
| 269 |
+
"learning_rate": 3.984972585121506e-05,
|
| 270 |
+
"loss": 33.97822265625,
|
| 271 |
+
"step": 3500
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.7071475925061999,
|
| 275 |
+
"grad_norm": 20.13410758972168,
|
| 276 |
+
"learning_rate": 3.9511270561158874e-05,
|
| 277 |
+
"loss": 34.1056494140625,
|
| 278 |
+
"step": 3600
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.7267905811869276,
|
| 282 |
+
"grad_norm": 18.82459259033203,
|
| 283 |
+
"learning_rate": 3.917281527110269e-05,
|
| 284 |
+
"loss": 34.2245947265625,
|
| 285 |
+
"step": 3700
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.7464335698676554,
|
| 289 |
+
"grad_norm": 17.352100372314453,
|
| 290 |
+
"learning_rate": 3.8834359981046505e-05,
|
| 291 |
+
"loss": 34.04242919921875,
|
| 292 |
+
"step": 3800
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.7495764480565718,
|
| 296 |
+
"eval_loss": 4.178581237792969,
|
| 297 |
+
"eval_runtime": 42.0642,
|
| 298 |
+
"eval_samples_per_second": 475.463,
|
| 299 |
+
"eval_steps_per_second": 14.858,
|
| 300 |
+
"step": 3816
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.7660765585483832,
|
| 304 |
+
"grad_norm": 19.103435516357422,
|
| 305 |
+
"learning_rate": 3.849590469099032e-05,
|
| 306 |
+
"loss": 34.01751708984375,
|
| 307 |
+
"step": 3900
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.7857195472291109,
|
| 311 |
+
"grad_norm": 18.045913696289062,
|
| 312 |
+
"learning_rate": 3.815744940093414e-05,
|
| 313 |
+
"loss": 33.90669921875,
|
| 314 |
+
"step": 4000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.8053625359098386,
|
| 318 |
+
"grad_norm": 18.76168441772461,
|
| 319 |
+
"learning_rate": 3.7818994110877956e-05,
|
| 320 |
+
"loss": 33.872587890625,
|
| 321 |
+
"step": 4100
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8250055245905664,
|
| 325 |
+
"grad_norm": 16.547574996948242,
|
| 326 |
+
"learning_rate": 3.748053882082177e-05,
|
| 327 |
+
"loss": 33.8643359375,
|
| 328 |
+
"step": 4200
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8446485132712942,
|
| 332 |
+
"grad_norm": 18.636455535888672,
|
| 333 |
+
"learning_rate": 3.714208353076559e-05,
|
| 334 |
+
"loss": 33.7685595703125,
|
| 335 |
+
"step": 4300
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.864291501952022,
|
| 339 |
+
"grad_norm": 18.742900848388672,
|
| 340 |
+
"learning_rate": 3.68036282407094e-05,
|
| 341 |
+
"loss": 33.53510009765625,
|
| 342 |
+
"step": 4400
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.8839344906327498,
|
| 346 |
+
"grad_norm": 20.976703643798828,
|
| 347 |
+
"learning_rate": 3.646517295065322e-05,
|
| 348 |
+
"loss": 33.42730224609375,
|
| 349 |
+
"step": 4500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.9035774793134775,
|
| 353 |
+
"grad_norm": 18.552316665649414,
|
| 354 |
+
"learning_rate": 3.612671766059704e-05,
|
| 355 |
+
"loss": 33.53127197265625,
|
| 356 |
+
"step": 4600
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.9232204679942053,
|
| 360 |
+
"grad_norm": 21.41478157043457,
|
| 361 |
+
"learning_rate": 3.578826237054085e-05,
|
| 362 |
+
"loss": 33.41383544921875,
|
| 363 |
+
"step": 4700
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9428634566749331,
|
| 367 |
+
"grad_norm": 19.785966873168945,
|
| 368 |
+
"learning_rate": 3.544980708048467e-05,
|
| 369 |
+
"loss": 33.38103271484375,
|
| 370 |
+
"step": 4800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.9625064453556609,
|
| 374 |
+
"grad_norm": 17.69455337524414,
|
| 375 |
+
"learning_rate": 3.511135179042849e-05,
|
| 376 |
+
"loss": 33.4733447265625,
|
| 377 |
+
"step": 4900
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.9821494340363887,
|
| 381 |
+
"grad_norm": 20.246673583984375,
|
| 382 |
+
"learning_rate": 3.47728965003723e-05,
|
| 383 |
+
"loss": 33.4089208984375,
|
| 384 |
+
"step": 5000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.999435264075429,
|
| 388 |
+
"eval_loss": 4.0612263679504395,
|
| 389 |
+
"eval_runtime": 42.4302,
|
| 390 |
+
"eval_samples_per_second": 471.362,
|
| 391 |
+
"eval_steps_per_second": 14.73,
|
| 392 |
+
"step": 5088
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.0017678689812655,
|
| 396 |
+
"grad_norm": 19.691932678222656,
|
| 397 |
+
"learning_rate": 3.443444121031612e-05,
|
| 398 |
+
"loss": 33.1838037109375,
|
| 399 |
+
"step": 5100
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.0214108576619934,
|
| 403 |
+
"grad_norm": 18.13388442993164,
|
| 404 |
+
"learning_rate": 3.409598592025994e-05,
|
| 405 |
+
"loss": 33.21130859375,
|
| 406 |
+
"step": 5200
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.041053846342721,
|
| 410 |
+
"grad_norm": 18.41756248474121,
|
| 411 |
+
"learning_rate": 3.375753063020375e-05,
|
| 412 |
+
"loss": 33.07806396484375,
|
| 413 |
+
"step": 5300
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.060696835023449,
|
| 417 |
+
"grad_norm": 18.85491943359375,
|
| 418 |
+
"learning_rate": 3.3419075340147566e-05,
|
| 419 |
+
"loss": 32.95417724609375,
|
| 420 |
+
"step": 5400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.0803398237041766,
|
| 424 |
+
"grad_norm": 20.03909683227539,
|
| 425 |
+
"learning_rate": 3.3080620050091385e-05,
|
| 426 |
+
"loss": 32.93142822265625,
|
| 427 |
+
"step": 5500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.0999828123849045,
|
| 431 |
+
"grad_norm": 19.49604606628418,
|
| 432 |
+
"learning_rate": 3.27421647600352e-05,
|
| 433 |
+
"loss": 32.9296630859375,
|
| 434 |
+
"step": 5600
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.1196258010656321,
|
| 438 |
+
"grad_norm": 21.259004592895508,
|
| 439 |
+
"learning_rate": 3.2403709469979017e-05,
|
| 440 |
+
"loss": 32.85189453125,
|
| 441 |
+
"step": 5700
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.1392687897463598,
|
| 445 |
+
"grad_norm": 19.597267150878906,
|
| 446 |
+
"learning_rate": 3.206525417992283e-05,
|
| 447 |
+
"loss": 32.82923583984375,
|
| 448 |
+
"step": 5800
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.1589117784270877,
|
| 452 |
+
"grad_norm": 20.224699020385742,
|
| 453 |
+
"learning_rate": 3.172679888986665e-05,
|
| 454 |
+
"loss": 32.7767626953125,
|
| 455 |
+
"step": 5900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.1785547671078154,
|
| 459 |
+
"grad_norm": 18.452495574951172,
|
| 460 |
+
"learning_rate": 3.138834359981047e-05,
|
| 461 |
+
"loss": 32.6592626953125,
|
| 462 |
+
"step": 6000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.1981977557885433,
|
| 466 |
+
"grad_norm": 19.971717834472656,
|
| 467 |
+
"learning_rate": 3.104988830975428e-05,
|
| 468 |
+
"loss": 32.80323974609375,
|
| 469 |
+
"step": 6100
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.217840744469271,
|
| 473 |
+
"grad_norm": 17.584882736206055,
|
| 474 |
+
"learning_rate": 3.07114330196981e-05,
|
| 475 |
+
"loss": 32.6551416015625,
|
| 476 |
+
"step": 6200
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.2374837331499988,
|
| 480 |
+
"grad_norm": 19.49502944946289,
|
| 481 |
+
"learning_rate": 3.0372977729641915e-05,
|
| 482 |
+
"loss": 32.73489990234375,
|
| 483 |
+
"step": 6300
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.2492695263584355,
|
| 487 |
+
"eval_loss": 3.9626989364624023,
|
| 488 |
+
"eval_runtime": 41.8921,
|
| 489 |
+
"eval_samples_per_second": 477.418,
|
| 490 |
+
"eval_steps_per_second": 14.919,
|
| 491 |
+
"step": 6360
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.2571267218307265,
|
| 495 |
+
"grad_norm": 20.214130401611328,
|
| 496 |
+
"learning_rate": 3.0034522439585734e-05,
|
| 497 |
+
"loss": 32.55817138671875,
|
| 498 |
+
"step": 6400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.2767697105114544,
|
| 502 |
+
"grad_norm": 20.668527603149414,
|
| 503 |
+
"learning_rate": 2.969606714952955e-05,
|
| 504 |
+
"loss": 32.53630615234375,
|
| 505 |
+
"step": 6500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.296412699192182,
|
| 509 |
+
"grad_norm": 18.479408264160156,
|
| 510 |
+
"learning_rate": 2.9357611859473366e-05,
|
| 511 |
+
"loss": 32.464462890625,
|
| 512 |
+
"step": 6600
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.31605568787291,
|
| 516 |
+
"grad_norm": 19.027793884277344,
|
| 517 |
+
"learning_rate": 2.9019156569417182e-05,
|
| 518 |
+
"loss": 32.48625244140625,
|
| 519 |
+
"step": 6700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.3356986765536376,
|
| 523 |
+
"grad_norm": 19.871105194091797,
|
| 524 |
+
"learning_rate": 2.8680701279361e-05,
|
| 525 |
+
"loss": 32.41595947265625,
|
| 526 |
+
"step": 6800
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.3553416652343655,
|
| 530 |
+
"grad_norm": 19.916994094848633,
|
| 531 |
+
"learning_rate": 2.8342245989304817e-05,
|
| 532 |
+
"loss": 32.11419921875,
|
| 533 |
+
"step": 6900
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.3749846539150932,
|
| 537 |
+
"grad_norm": 21.212909698486328,
|
| 538 |
+
"learning_rate": 2.8003790699248633e-05,
|
| 539 |
+
"loss": 32.30314453125,
|
| 540 |
+
"step": 7000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.3946276425958208,
|
| 544 |
+
"grad_norm": 25.216768264770508,
|
| 545 |
+
"learning_rate": 2.7665335409192445e-05,
|
| 546 |
+
"loss": 32.19344482421875,
|
| 547 |
+
"step": 7100
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.4142706312765487,
|
| 551 |
+
"grad_norm": 19.619844436645508,
|
| 552 |
+
"learning_rate": 2.732688011913626e-05,
|
| 553 |
+
"loss": 32.30953125,
|
| 554 |
+
"step": 7200
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.4339136199572766,
|
| 558 |
+
"grad_norm": 21.061376571655273,
|
| 559 |
+
"learning_rate": 2.6988424829080077e-05,
|
| 560 |
+
"loss": 32.3416162109375,
|
| 561 |
+
"step": 7300
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.4535566086380043,
|
| 565 |
+
"grad_norm": 18.674562454223633,
|
| 566 |
+
"learning_rate": 2.6649969539023896e-05,
|
| 567 |
+
"loss": 32.2662744140625,
|
| 568 |
+
"step": 7400
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.473199597318732,
|
| 572 |
+
"grad_norm": 18.776655197143555,
|
| 573 |
+
"learning_rate": 2.6311514248967712e-05,
|
| 574 |
+
"loss": 32.07302978515625,
|
| 575 |
+
"step": 7500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.4928425859994598,
|
| 579 |
+
"grad_norm": 19.0480899810791,
|
| 580 |
+
"learning_rate": 2.5973058958911528e-05,
|
| 581 |
+
"loss": 32.19434326171875,
|
| 582 |
+
"step": 7600
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.4991283423772928,
|
| 586 |
+
"eval_loss": 3.9200026988983154,
|
| 587 |
+
"eval_runtime": 42.1732,
|
| 588 |
+
"eval_samples_per_second": 474.235,
|
| 589 |
+
"eval_steps_per_second": 14.82,
|
| 590 |
+
"step": 7632
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.5124855746801877,
|
| 594 |
+
"grad_norm": 18.192241668701172,
|
| 595 |
+
"learning_rate": 2.5634603668855344e-05,
|
| 596 |
+
"loss": 32.0382470703125,
|
| 597 |
+
"step": 7700
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.5321285633609154,
|
| 601 |
+
"grad_norm": 21.64850425720215,
|
| 602 |
+
"learning_rate": 2.5296148378799163e-05,
|
| 603 |
+
"loss": 32.0071484375,
|
| 604 |
+
"step": 7800
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.551771552041643,
|
| 608 |
+
"grad_norm": 21.07256507873535,
|
| 609 |
+
"learning_rate": 2.495769308874298e-05,
|
| 610 |
+
"loss": 32.02736328125,
|
| 611 |
+
"step": 7900
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.5714145407223707,
|
| 615 |
+
"grad_norm": 18.811485290527344,
|
| 616 |
+
"learning_rate": 2.4619237798686794e-05,
|
| 617 |
+
"loss": 32.18232666015625,
|
| 618 |
+
"step": 8000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.5910575294030986,
|
| 622 |
+
"grad_norm": 20.226411819458008,
|
| 623 |
+
"learning_rate": 2.428078250863061e-05,
|
| 624 |
+
"loss": 31.81751220703125,
|
| 625 |
+
"step": 8100
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6107005180838265,
|
| 629 |
+
"grad_norm": 21.44918441772461,
|
| 630 |
+
"learning_rate": 2.394232721857443e-05,
|
| 631 |
+
"loss": 31.89043212890625,
|
| 632 |
+
"step": 8200
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.6303435067645542,
|
| 636 |
+
"grad_norm": 19.660367965698242,
|
| 637 |
+
"learning_rate": 2.3603871928518245e-05,
|
| 638 |
+
"loss": 31.95683349609375,
|
| 639 |
+
"step": 8300
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.6499864954452819,
|
| 643 |
+
"grad_norm": 19.144596099853516,
|
| 644 |
+
"learning_rate": 2.3265416638462058e-05,
|
| 645 |
+
"loss": 31.867197265625,
|
| 646 |
+
"step": 8400
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.6696294841260098,
|
| 650 |
+
"grad_norm": 18.604026794433594,
|
| 651 |
+
"learning_rate": 2.2926961348405877e-05,
|
| 652 |
+
"loss": 31.78265380859375,
|
| 653 |
+
"step": 8500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.6892724728067376,
|
| 657 |
+
"grad_norm": 19.978652954101562,
|
| 658 |
+
"learning_rate": 2.2588506058349693e-05,
|
| 659 |
+
"loss": 31.79925048828125,
|
| 660 |
+
"step": 8600
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.7089154614874653,
|
| 664 |
+
"grad_norm": 18.18141746520996,
|
| 665 |
+
"learning_rate": 2.225005076829351e-05,
|
| 666 |
+
"loss": 31.853974609375,
|
| 667 |
+
"step": 8700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.728558450168193,
|
| 671 |
+
"grad_norm": 17.99820899963379,
|
| 672 |
+
"learning_rate": 2.1911595478237325e-05,
|
| 673 |
+
"loss": 31.75265625,
|
| 674 |
+
"step": 8800
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.7482014388489209,
|
| 678 |
+
"grad_norm": 20.680606842041016,
|
| 679 |
+
"learning_rate": 2.1573140188181144e-05,
|
| 680 |
+
"loss": 31.6561328125,
|
| 681 |
+
"step": 8900
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.74898715839615,
|
| 685 |
+
"eval_loss": 3.863434076309204,
|
| 686 |
+
"eval_runtime": 42.0055,
|
| 687 |
+
"eval_samples_per_second": 476.128,
|
| 688 |
+
"eval_steps_per_second": 14.879,
|
| 689 |
+
"step": 8904
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.7678444275296488,
|
| 693 |
+
"grad_norm": 20.50802993774414,
|
| 694 |
+
"learning_rate": 2.123468489812496e-05,
|
| 695 |
+
"loss": 31.6072265625,
|
| 696 |
+
"step": 9000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.7874874162103764,
|
| 700 |
+
"grad_norm": 21.482328414916992,
|
| 701 |
+
"learning_rate": 2.0896229608068775e-05,
|
| 702 |
+
"loss": 31.7250537109375,
|
| 703 |
+
"step": 9100
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.807130404891104,
|
| 707 |
+
"grad_norm": 19.20509910583496,
|
| 708 |
+
"learning_rate": 2.055777431801259e-05,
|
| 709 |
+
"loss": 31.58796875,
|
| 710 |
+
"step": 9200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.826773393571832,
|
| 714 |
+
"grad_norm": 21.03694725036621,
|
| 715 |
+
"learning_rate": 2.0219319027956407e-05,
|
| 716 |
+
"loss": 31.68398193359375,
|
| 717 |
+
"step": 9300
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.8464163822525599,
|
| 721 |
+
"grad_norm": 18.272459030151367,
|
| 722 |
+
"learning_rate": 1.9880863737900223e-05,
|
| 723 |
+
"loss": 31.53086181640625,
|
| 724 |
+
"step": 9400
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.8660593709332876,
|
| 728 |
+
"grad_norm": 19.046916961669922,
|
| 729 |
+
"learning_rate": 1.9542408447844042e-05,
|
| 730 |
+
"loss": 31.525322265625,
|
| 731 |
+
"step": 9500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.8857023596140152,
|
| 735 |
+
"grad_norm": 21.118305206298828,
|
| 736 |
+
"learning_rate": 1.9203953157787858e-05,
|
| 737 |
+
"loss": 31.52841552734375,
|
| 738 |
+
"step": 9600
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.905345348294743,
|
| 742 |
+
"grad_norm": 18.861080169677734,
|
| 743 |
+
"learning_rate": 1.8865497867731674e-05,
|
| 744 |
+
"loss": 31.4529345703125,
|
| 745 |
+
"step": 9700
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.9249883369754708,
|
| 749 |
+
"grad_norm": 20.4729061126709,
|
| 750 |
+
"learning_rate": 1.852704257767549e-05,
|
| 751 |
+
"loss": 31.35305419921875,
|
| 752 |
+
"step": 9800
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.9446313256561987,
|
| 756 |
+
"grad_norm": 17.702392578125,
|
| 757 |
+
"learning_rate": 1.818858728761931e-05,
|
| 758 |
+
"loss": 31.5552734375,
|
| 759 |
+
"step": 9900
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.9642743143369263,
|
| 763 |
+
"grad_norm": 21.927942276000977,
|
| 764 |
+
"learning_rate": 1.785013199756312e-05,
|
| 765 |
+
"loss": 31.42951416015625,
|
| 766 |
+
"step": 10000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.983917303017654,
|
| 770 |
+
"grad_norm": 19.895252227783203,
|
| 771 |
+
"learning_rate": 1.7511676707506937e-05,
|
| 772 |
+
"loss": 31.416962890625,
|
| 773 |
+
"step": 10100
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.998845974415007,
|
| 777 |
+
"eval_loss": 3.819389820098877,
|
| 778 |
+
"eval_runtime": 41.9176,
|
| 779 |
+
"eval_samples_per_second": 477.126,
|
| 780 |
+
"eval_steps_per_second": 14.91,
|
| 781 |
+
"step": 10176
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.003535737962531,
|
| 785 |
+
"grad_norm": 20.209577560424805,
|
| 786 |
+
"learning_rate": 1.7173221417450756e-05,
|
| 787 |
+
"loss": 31.25757568359375,
|
| 788 |
+
"step": 10200
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.0231787266432586,
|
| 792 |
+
"grad_norm": 19.49869155883789,
|
| 793 |
+
"learning_rate": 1.6834766127394572e-05,
|
| 794 |
+
"loss": 31.14395263671875,
|
| 795 |
+
"step": 10300
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.0428217153239867,
|
| 799 |
+
"grad_norm": 20.60426139831543,
|
| 800 |
+
"learning_rate": 1.6496310837338388e-05,
|
| 801 |
+
"loss": 31.38017333984375,
|
| 802 |
+
"step": 10400
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.0624647040047144,
|
| 806 |
+
"grad_norm": 19.177818298339844,
|
| 807 |
+
"learning_rate": 1.6157855547282204e-05,
|
| 808 |
+
"loss": 31.20944091796875,
|
| 809 |
+
"step": 10500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.082107692685442,
|
| 813 |
+
"grad_norm": 20.949337005615234,
|
| 814 |
+
"learning_rate": 1.5819400257226023e-05,
|
| 815 |
+
"loss": 31.2146240234375,
|
| 816 |
+
"step": 10600
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.1017506813661697,
|
| 820 |
+
"grad_norm": 19.25591468811035,
|
| 821 |
+
"learning_rate": 1.548094496716984e-05,
|
| 822 |
+
"loss": 31.202607421875,
|
| 823 |
+
"step": 10700
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.121393670046898,
|
| 827 |
+
"grad_norm": 18.960092544555664,
|
| 828 |
+
"learning_rate": 1.5142489677113653e-05,
|
| 829 |
+
"loss": 31.14611572265625,
|
| 830 |
+
"step": 10800
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.1410366587276255,
|
| 834 |
+
"grad_norm": 18.479068756103516,
|
| 835 |
+
"learning_rate": 1.4804034387057469e-05,
|
| 836 |
+
"loss": 31.26153564453125,
|
| 837 |
+
"step": 10900
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.160679647408353,
|
| 841 |
+
"grad_norm": 21.587387084960938,
|
| 842 |
+
"learning_rate": 1.4465579097001287e-05,
|
| 843 |
+
"loss": 31.1222998046875,
|
| 844 |
+
"step": 11000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.180322636089081,
|
| 848 |
+
"grad_norm": 17.947052001953125,
|
| 849 |
+
"learning_rate": 1.4127123806945102e-05,
|
| 850 |
+
"loss": 31.08917236328125,
|
| 851 |
+
"step": 11100
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.199965624769809,
|
| 855 |
+
"grad_norm": 19.169307708740234,
|
| 856 |
+
"learning_rate": 1.378866851688892e-05,
|
| 857 |
+
"loss": 31.0661474609375,
|
| 858 |
+
"step": 11200
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.2196086134505366,
|
| 862 |
+
"grad_norm": 16.882522583007812,
|
| 863 |
+
"learning_rate": 1.3450213226832736e-05,
|
| 864 |
+
"loss": 30.9886328125,
|
| 865 |
+
"step": 11300
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.2392516021312643,
|
| 869 |
+
"grad_norm": 19.624177932739258,
|
| 870 |
+
"learning_rate": 1.3111757936776553e-05,
|
| 871 |
+
"loss": 30.93468505859375,
|
| 872 |
+
"step": 11400
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.2486802366980134,
|
| 876 |
+
"eval_loss": 3.786958694458008,
|
| 877 |
+
"eval_runtime": 41.8524,
|
| 878 |
+
"eval_samples_per_second": 477.869,
|
| 879 |
+
"eval_steps_per_second": 14.933,
|
| 880 |
+
"step": 11448
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.258894590811992,
|
| 884 |
+
"grad_norm": 20.477542877197266,
|
| 885 |
+
"learning_rate": 1.2773302646720369e-05,
|
| 886 |
+
"loss": 31.00721923828125,
|
| 887 |
+
"step": 11500
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.2785375794927196,
|
| 891 |
+
"grad_norm": 19.928098678588867,
|
| 892 |
+
"learning_rate": 1.2434847356664185e-05,
|
| 893 |
+
"loss": 30.95269775390625,
|
| 894 |
+
"step": 11600
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.2981805681734477,
|
| 898 |
+
"grad_norm": 19.002788543701172,
|
| 899 |
+
"learning_rate": 1.2096392066608003e-05,
|
| 900 |
+
"loss": 30.908701171875,
|
| 901 |
+
"step": 11700
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.3178235568541754,
|
| 905 |
+
"grad_norm": 20.50242805480957,
|
| 906 |
+
"learning_rate": 1.1757936776551818e-05,
|
| 907 |
+
"loss": 30.96546142578125,
|
| 908 |
+
"step": 11800
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.337466545534903,
|
| 912 |
+
"grad_norm": 20.48063850402832,
|
| 913 |
+
"learning_rate": 1.1419481486495634e-05,
|
| 914 |
+
"loss": 30.9563623046875,
|
| 915 |
+
"step": 11900
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.3571095342156307,
|
| 919 |
+
"grad_norm": 19.522266387939453,
|
| 920 |
+
"learning_rate": 1.108102619643945e-05,
|
| 921 |
+
"loss": 30.85960205078125,
|
| 922 |
+
"step": 12000
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.376752522896359,
|
| 926 |
+
"grad_norm": 21.33004379272461,
|
| 927 |
+
"learning_rate": 1.0742570906383268e-05,
|
| 928 |
+
"loss": 30.829111328125,
|
| 929 |
+
"step": 12100
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.3963955115770865,
|
| 933 |
+
"grad_norm": 20.311534881591797,
|
| 934 |
+
"learning_rate": 1.0404115616327083e-05,
|
| 935 |
+
"loss": 30.93859619140625,
|
| 936 |
+
"step": 12200
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.416038500257814,
|
| 940 |
+
"grad_norm": 20.128795623779297,
|
| 941 |
+
"learning_rate": 1.00656603262709e-05,
|
| 942 |
+
"loss": 30.750810546875,
|
| 943 |
+
"step": 12300
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.435681488938542,
|
| 947 |
+
"grad_norm": 22.28921890258789,
|
| 948 |
+
"learning_rate": 9.727205036214717e-06,
|
| 949 |
+
"loss": 30.714560546875,
|
| 950 |
+
"step": 12400
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.4553244776192695,
|
| 954 |
+
"grad_norm": 24.13454818725586,
|
| 955 |
+
"learning_rate": 9.388749746158533e-06,
|
| 956 |
+
"loss": 30.87623779296875,
|
| 957 |
+
"step": 12500
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.4749674662999976,
|
| 961 |
+
"grad_norm": 20.58381462097168,
|
| 962 |
+
"learning_rate": 9.05029445610235e-06,
|
| 963 |
+
"loss": 30.60492431640625,
|
| 964 |
+
"step": 12600
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.4946104549807253,
|
| 968 |
+
"grad_norm": 20.045475006103516,
|
| 969 |
+
"learning_rate": 8.711839166046164e-06,
|
| 970 |
+
"loss": 30.8008154296875,
|
| 971 |
+
"step": 12700
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.498539052716871,
|
| 975 |
+
"eval_loss": 3.7586019039154053,
|
| 976 |
+
"eval_runtime": 42.0034,
|
| 977 |
+
"eval_samples_per_second": 476.152,
|
| 978 |
+
"eval_steps_per_second": 14.88,
|
| 979 |
+
"step": 12720
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 2.514253443661453,
|
| 983 |
+
"grad_norm": 19.53034210205078,
|
| 984 |
+
"learning_rate": 8.373383875989982e-06,
|
| 985 |
+
"loss": 30.7534326171875,
|
| 986 |
+
"step": 12800
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.533896432342181,
|
| 990 |
+
"grad_norm": 20.510520935058594,
|
| 991 |
+
"learning_rate": 8.0349285859338e-06,
|
| 992 |
+
"loss": 30.7755859375,
|
| 993 |
+
"step": 12900
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.5535394210229088,
|
| 997 |
+
"grad_norm": 20.725147247314453,
|
| 998 |
+
"learning_rate": 7.696473295877615e-06,
|
| 999 |
+
"loss": 30.9005029296875,
|
| 1000 |
+
"step": 13000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.5731824097036364,
|
| 1004 |
+
"grad_norm": 20.11240577697754,
|
| 1005 |
+
"learning_rate": 7.358018005821431e-06,
|
| 1006 |
+
"loss": 30.81609130859375,
|
| 1007 |
+
"step": 13100
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 2.592825398384364,
|
| 1011 |
+
"grad_norm": 19.01041603088379,
|
| 1012 |
+
"learning_rate": 7.019562715765248e-06,
|
| 1013 |
+
"loss": 30.70421142578125,
|
| 1014 |
+
"step": 13200
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.6124683870650918,
|
| 1018 |
+
"grad_norm": 20.232532501220703,
|
| 1019 |
+
"learning_rate": 6.681107425709064e-06,
|
| 1020 |
+
"loss": 30.7105322265625,
|
| 1021 |
+
"step": 13300
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.63211137574582,
|
| 1025 |
+
"grad_norm": 21.33913803100586,
|
| 1026 |
+
"learning_rate": 6.342652135652881e-06,
|
| 1027 |
+
"loss": 30.76764892578125,
|
| 1028 |
+
"step": 13400
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.6517543644265475,
|
| 1032 |
+
"grad_norm": 19.718833923339844,
|
| 1033 |
+
"learning_rate": 6.004196845596697e-06,
|
| 1034 |
+
"loss": 30.75705078125,
|
| 1035 |
+
"step": 13500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.671397353107275,
|
| 1039 |
+
"grad_norm": 20.983705520629883,
|
| 1040 |
+
"learning_rate": 5.665741555540514e-06,
|
| 1041 |
+
"loss": 30.66492431640625,
|
| 1042 |
+
"step": 13600
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 2.691040341788003,
|
| 1046 |
+
"grad_norm": 18.726970672607422,
|
| 1047 |
+
"learning_rate": 5.3272862654843295e-06,
|
| 1048 |
+
"loss": 30.72262451171875,
|
| 1049 |
+
"step": 13700
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.710683330468731,
|
| 1053 |
+
"grad_norm": 21.197751998901367,
|
| 1054 |
+
"learning_rate": 4.988830975428146e-06,
|
| 1055 |
+
"loss": 30.6771728515625,
|
| 1056 |
+
"step": 13800
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 2.7303263191494587,
|
| 1060 |
+
"grad_norm": 21.318998336791992,
|
| 1061 |
+
"learning_rate": 4.650375685371963e-06,
|
| 1062 |
+
"loss": 30.52608642578125,
|
| 1063 |
+
"step": 13900
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 2.748397868735728,
|
| 1067 |
+
"eval_loss": 3.7217817306518555,
|
| 1068 |
+
"eval_runtime": 41.8977,
|
| 1069 |
+
"eval_samples_per_second": 477.353,
|
| 1070 |
+
"eval_steps_per_second": 14.917,
|
| 1071 |
+
"step": 13992
|
| 1072 |
+
}
|
| 1073 |
+
],
|
| 1074 |
+
"logging_steps": 100,
|
| 1075 |
+
"max_steps": 15273,
|
| 1076 |
+
"num_input_tokens_seen": 0,
|
| 1077 |
+
"num_train_epochs": 3,
|
| 1078 |
+
"save_steps": 1272,
|
| 1079 |
+
"stateful_callbacks": {
|
| 1080 |
+
"TrainerControl": {
|
| 1081 |
+
"args": {
|
| 1082 |
+
"should_epoch_stop": false,
|
| 1083 |
+
"should_evaluate": false,
|
| 1084 |
+
"should_log": false,
|
| 1085 |
+
"should_save": true,
|
| 1086 |
+
"should_training_stop": false
|
| 1087 |
+
},
|
| 1088 |
+
"attributes": {}
|
| 1089 |
+
}
|
| 1090 |
+
},
|
| 1091 |
+
"total_flos": 9.427785384950231e+17,
|
| 1092 |
+
"train_batch_size": 32,
|
| 1093 |
+
"trial_name": null,
|
| 1094 |
+
"trial_params": null
|
| 1095 |
+
}
|
checkpoint-13992/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaec524752280134c2e0387d7f5f1e2cc6d34eaa3f289327a642e9b1d7d2b9c9
|
| 3 |
+
size 5137
|
checkpoint-15273/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "roberta",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"transformers_version": "5.0.0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 32001
|
| 28 |
+
}
|
checkpoint-15273/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e84d91ed965ee8a4304e29704132a4eb31a020da83620feeb85893d674be3ef
|
| 3 |
+
size 442633860
|
checkpoint-15273/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:936ee266876e662dcf56a141dcffd2bdef49fc3fb413397030a5008dea1a9577
|
| 3 |
+
size 885391563
|
checkpoint-15273/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c587c86f3d5a4c4b98c761a28cc64fdb870f6214dbf5835d1fcb43dedf56307
|
| 3 |
+
size 14645
|
checkpoint-15273/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbf8b230b03e6bd05860655271ad5a73c7151e2784bd60ccf16d5bcc0db59048
|
| 3 |
+
size 1383
|
checkpoint-15273/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f78a79bb217a80efbb6f1c2b98c1488f65ab61871236f43f21776e7b9d42b60
|
| 3 |
+
size 1465
|
checkpoint-15273/trainer_state.json
ADDED
|
@@ -0,0 +1,1194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 13992,
|
| 3 |
+
"best_metric": 3.7217817306518555,
|
| 4 |
+
"best_model_checkpoint": "sindhibert_session2/checkpoint-13992",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 1272,
|
| 7 |
+
"global_step": 15273,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.019642988680727773,
|
| 14 |
+
"grad_norm": 16.122173309326172,
|
| 15 |
+
"learning_rate": 9.900000000000002e-06,
|
| 16 |
+
"loss": 36.5051904296875,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.039285977361455546,
|
| 21 |
+
"grad_norm": 18.11626434326172,
|
| 22 |
+
"learning_rate": 1.9900000000000003e-05,
|
| 23 |
+
"loss": 36.368505859375,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05892896604218332,
|
| 28 |
+
"grad_norm": 18.927509307861328,
|
| 29 |
+
"learning_rate": 2.9900000000000002e-05,
|
| 30 |
+
"loss": 36.45832275390625,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07857195472291109,
|
| 35 |
+
"grad_norm": 18.480167388916016,
|
| 36 |
+
"learning_rate": 3.99e-05,
|
| 37 |
+
"loss": 36.31460693359375,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09821494340363886,
|
| 42 |
+
"grad_norm": 19.010652542114258,
|
| 43 |
+
"learning_rate": 4.99e-05,
|
| 44 |
+
"loss": 36.24136962890625,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11785793208436664,
|
| 49 |
+
"grad_norm": 19.11362075805664,
|
| 50 |
+
"learning_rate": 4.966492926284438e-05,
|
| 51 |
+
"loss": 36.54402587890625,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1375009207650944,
|
| 56 |
+
"grad_norm": 19.41926383972168,
|
| 57 |
+
"learning_rate": 4.93264739727882e-05,
|
| 58 |
+
"loss": 36.28423095703125,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15714390944582218,
|
| 63 |
+
"grad_norm": 20.20358657836914,
|
| 64 |
+
"learning_rate": 4.898801868273201e-05,
|
| 65 |
+
"loss": 36.2180615234375,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.17678689812654996,
|
| 70 |
+
"grad_norm": 18.598957061767578,
|
| 71 |
+
"learning_rate": 4.864956339267583e-05,
|
| 72 |
+
"loss": 36.1883984375,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.19642988680727771,
|
| 77 |
+
"grad_norm": 18.320087432861328,
|
| 78 |
+
"learning_rate": 4.831110810261965e-05,
|
| 79 |
+
"loss": 36.0933837890625,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2160728754880055,
|
| 84 |
+
"grad_norm": 21.353364944458008,
|
| 85 |
+
"learning_rate": 4.797265281256346e-05,
|
| 86 |
+
"loss": 35.95175048828125,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.23571586416873327,
|
| 91 |
+
"grad_norm": 19.709365844726562,
|
| 92 |
+
"learning_rate": 4.763419752250728e-05,
|
| 93 |
+
"loss": 35.99169921875,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.24985881601885726,
|
| 98 |
+
"eval_loss": 4.386976718902588,
|
| 99 |
+
"eval_runtime": 41.9212,
|
| 100 |
+
"eval_samples_per_second": 477.086,
|
| 101 |
+
"eval_steps_per_second": 14.909,
|
| 102 |
+
"step": 1272
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.255358852849461,
|
| 106 |
+
"grad_norm": 17.78667449951172,
|
| 107 |
+
"learning_rate": 4.729574223245109e-05,
|
| 108 |
+
"loss": 35.86061279296875,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2750018415301888,
|
| 113 |
+
"grad_norm": 21.036474227905273,
|
| 114 |
+
"learning_rate": 4.695728694239491e-05,
|
| 115 |
+
"loss": 35.78255859375,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2946448302109166,
|
| 120 |
+
"grad_norm": 19.002052307128906,
|
| 121 |
+
"learning_rate": 4.661883165233873e-05,
|
| 122 |
+
"loss": 35.5993408203125,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.31428781889164437,
|
| 127 |
+
"grad_norm": 19.828800201416016,
|
| 128 |
+
"learning_rate": 4.6280376362282543e-05,
|
| 129 |
+
"loss": 35.70918701171875,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.33393080757237215,
|
| 134 |
+
"grad_norm": 17.12042236328125,
|
| 135 |
+
"learning_rate": 4.594192107222636e-05,
|
| 136 |
+
"loss": 35.58583251953125,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3535737962530999,
|
| 141 |
+
"grad_norm": 19.869712829589844,
|
| 142 |
+
"learning_rate": 4.560346578217018e-05,
|
| 143 |
+
"loss": 35.3600537109375,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3732167849338277,
|
| 148 |
+
"grad_norm": 18.914470672607422,
|
| 149 |
+
"learning_rate": 4.5265010492113994e-05,
|
| 150 |
+
"loss": 35.34132080078125,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.39285977361455543,
|
| 155 |
+
"grad_norm": 18.888940811157227,
|
| 156 |
+
"learning_rate": 4.4926555202057814e-05,
|
| 157 |
+
"loss": 35.33590576171875,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.4125027622952832,
|
| 162 |
+
"grad_norm": 20.27227783203125,
|
| 163 |
+
"learning_rate": 4.4588099912001626e-05,
|
| 164 |
+
"loss": 35.22805908203125,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.432145750976011,
|
| 169 |
+
"grad_norm": 15.550501823425293,
|
| 170 |
+
"learning_rate": 4.424964462194544e-05,
|
| 171 |
+
"loss": 35.256953125,
|
| 172 |
+
"step": 2200
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.45178873965673877,
|
| 176 |
+
"grad_norm": 17.671451568603516,
|
| 177 |
+
"learning_rate": 4.391118933188926e-05,
|
| 178 |
+
"loss": 35.056826171875,
|
| 179 |
+
"step": 2300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.47143172833746655,
|
| 183 |
+
"grad_norm": 18.74838638305664,
|
| 184 |
+
"learning_rate": 4.357273404183308e-05,
|
| 185 |
+
"loss": 34.9271826171875,
|
| 186 |
+
"step": 2400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.49107471701819433,
|
| 190 |
+
"grad_norm": 20.912931442260742,
|
| 191 |
+
"learning_rate": 4.323427875177689e-05,
|
| 192 |
+
"loss": 34.793916015625,
|
| 193 |
+
"step": 2500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.4997176320377145,
|
| 197 |
+
"eval_loss": 4.270185947418213,
|
| 198 |
+
"eval_runtime": 41.8695,
|
| 199 |
+
"eval_samples_per_second": 477.675,
|
| 200 |
+
"eval_steps_per_second": 14.927,
|
| 201 |
+
"step": 2544
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.510717705698922,
|
| 205 |
+
"grad_norm": 18.11321258544922,
|
| 206 |
+
"learning_rate": 4.289582346172071e-05,
|
| 207 |
+
"loss": 34.97314453125,
|
| 208 |
+
"step": 2600
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.5303606943796498,
|
| 212 |
+
"grad_norm": 19.38896942138672,
|
| 213 |
+
"learning_rate": 4.255736817166453e-05,
|
| 214 |
+
"loss": 34.873974609375,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5500036830603776,
|
| 219 |
+
"grad_norm": 19.479278564453125,
|
| 220 |
+
"learning_rate": 4.221891288160834e-05,
|
| 221 |
+
"loss": 34.713251953125,
|
| 222 |
+
"step": 2800
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5696466717411054,
|
| 226 |
+
"grad_norm": 19.849210739135742,
|
| 227 |
+
"learning_rate": 4.188045759155216e-05,
|
| 228 |
+
"loss": 34.66454833984375,
|
| 229 |
+
"step": 2900
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5892896604218332,
|
| 233 |
+
"grad_norm": 19.59630012512207,
|
| 234 |
+
"learning_rate": 4.154200230149597e-05,
|
| 235 |
+
"loss": 34.546259765625,
|
| 236 |
+
"step": 3000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.608932649102561,
|
| 240 |
+
"grad_norm": 18.32138442993164,
|
| 241 |
+
"learning_rate": 4.120354701143979e-05,
|
| 242 |
+
"loss": 34.460576171875,
|
| 243 |
+
"step": 3100
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.6285756377832887,
|
| 247 |
+
"grad_norm": 17.825464248657227,
|
| 248 |
+
"learning_rate": 4.086509172138361e-05,
|
| 249 |
+
"loss": 34.3186962890625,
|
| 250 |
+
"step": 3200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.6482186264640165,
|
| 254 |
+
"grad_norm": 19.180105209350586,
|
| 255 |
+
"learning_rate": 4.052663643132742e-05,
|
| 256 |
+
"loss": 34.40132080078125,
|
| 257 |
+
"step": 3300
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.6678616151447443,
|
| 261 |
+
"grad_norm": 18.498641967773438,
|
| 262 |
+
"learning_rate": 4.018818114127124e-05,
|
| 263 |
+
"loss": 34.2248828125,
|
| 264 |
+
"step": 3400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.6875046038254721,
|
| 268 |
+
"grad_norm": 19.08323097229004,
|
| 269 |
+
"learning_rate": 3.984972585121506e-05,
|
| 270 |
+
"loss": 33.97822265625,
|
| 271 |
+
"step": 3500
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.7071475925061999,
|
| 275 |
+
"grad_norm": 20.13410758972168,
|
| 276 |
+
"learning_rate": 3.9511270561158874e-05,
|
| 277 |
+
"loss": 34.1056494140625,
|
| 278 |
+
"step": 3600
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.7267905811869276,
|
| 282 |
+
"grad_norm": 18.82459259033203,
|
| 283 |
+
"learning_rate": 3.917281527110269e-05,
|
| 284 |
+
"loss": 34.2245947265625,
|
| 285 |
+
"step": 3700
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.7464335698676554,
|
| 289 |
+
"grad_norm": 17.352100372314453,
|
| 290 |
+
"learning_rate": 3.8834359981046505e-05,
|
| 291 |
+
"loss": 34.04242919921875,
|
| 292 |
+
"step": 3800
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.7495764480565718,
|
| 296 |
+
"eval_loss": 4.178581237792969,
|
| 297 |
+
"eval_runtime": 42.0642,
|
| 298 |
+
"eval_samples_per_second": 475.463,
|
| 299 |
+
"eval_steps_per_second": 14.858,
|
| 300 |
+
"step": 3816
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.7660765585483832,
|
| 304 |
+
"grad_norm": 19.103435516357422,
|
| 305 |
+
"learning_rate": 3.849590469099032e-05,
|
| 306 |
+
"loss": 34.01751708984375,
|
| 307 |
+
"step": 3900
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.7857195472291109,
|
| 311 |
+
"grad_norm": 18.045913696289062,
|
| 312 |
+
"learning_rate": 3.815744940093414e-05,
|
| 313 |
+
"loss": 33.90669921875,
|
| 314 |
+
"step": 4000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.8053625359098386,
|
| 318 |
+
"grad_norm": 18.76168441772461,
|
| 319 |
+
"learning_rate": 3.7818994110877956e-05,
|
| 320 |
+
"loss": 33.872587890625,
|
| 321 |
+
"step": 4100
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8250055245905664,
|
| 325 |
+
"grad_norm": 16.547574996948242,
|
| 326 |
+
"learning_rate": 3.748053882082177e-05,
|
| 327 |
+
"loss": 33.8643359375,
|
| 328 |
+
"step": 4200
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8446485132712942,
|
| 332 |
+
"grad_norm": 18.636455535888672,
|
| 333 |
+
"learning_rate": 3.714208353076559e-05,
|
| 334 |
+
"loss": 33.7685595703125,
|
| 335 |
+
"step": 4300
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.864291501952022,
|
| 339 |
+
"grad_norm": 18.742900848388672,
|
| 340 |
+
"learning_rate": 3.68036282407094e-05,
|
| 341 |
+
"loss": 33.53510009765625,
|
| 342 |
+
"step": 4400
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.8839344906327498,
|
| 346 |
+
"grad_norm": 20.976703643798828,
|
| 347 |
+
"learning_rate": 3.646517295065322e-05,
|
| 348 |
+
"loss": 33.42730224609375,
|
| 349 |
+
"step": 4500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.9035774793134775,
|
| 353 |
+
"grad_norm": 18.552316665649414,
|
| 354 |
+
"learning_rate": 3.612671766059704e-05,
|
| 355 |
+
"loss": 33.53127197265625,
|
| 356 |
+
"step": 4600
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.9232204679942053,
|
| 360 |
+
"grad_norm": 21.41478157043457,
|
| 361 |
+
"learning_rate": 3.578826237054085e-05,
|
| 362 |
+
"loss": 33.41383544921875,
|
| 363 |
+
"step": 4700
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9428634566749331,
|
| 367 |
+
"grad_norm": 19.785966873168945,
|
| 368 |
+
"learning_rate": 3.544980708048467e-05,
|
| 369 |
+
"loss": 33.38103271484375,
|
| 370 |
+
"step": 4800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.9625064453556609,
|
| 374 |
+
"grad_norm": 17.69455337524414,
|
| 375 |
+
"learning_rate": 3.511135179042849e-05,
|
| 376 |
+
"loss": 33.4733447265625,
|
| 377 |
+
"step": 4900
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.9821494340363887,
|
| 381 |
+
"grad_norm": 20.246673583984375,
|
| 382 |
+
"learning_rate": 3.47728965003723e-05,
|
| 383 |
+
"loss": 33.4089208984375,
|
| 384 |
+
"step": 5000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.999435264075429,
|
| 388 |
+
"eval_loss": 4.0612263679504395,
|
| 389 |
+
"eval_runtime": 42.4302,
|
| 390 |
+
"eval_samples_per_second": 471.362,
|
| 391 |
+
"eval_steps_per_second": 14.73,
|
| 392 |
+
"step": 5088
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.0017678689812655,
|
| 396 |
+
"grad_norm": 19.691932678222656,
|
| 397 |
+
"learning_rate": 3.443444121031612e-05,
|
| 398 |
+
"loss": 33.1838037109375,
|
| 399 |
+
"step": 5100
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.0214108576619934,
|
| 403 |
+
"grad_norm": 18.13388442993164,
|
| 404 |
+
"learning_rate": 3.409598592025994e-05,
|
| 405 |
+
"loss": 33.21130859375,
|
| 406 |
+
"step": 5200
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.041053846342721,
|
| 410 |
+
"grad_norm": 18.41756248474121,
|
| 411 |
+
"learning_rate": 3.375753063020375e-05,
|
| 412 |
+
"loss": 33.07806396484375,
|
| 413 |
+
"step": 5300
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.060696835023449,
|
| 417 |
+
"grad_norm": 18.85491943359375,
|
| 418 |
+
"learning_rate": 3.3419075340147566e-05,
|
| 419 |
+
"loss": 32.95417724609375,
|
| 420 |
+
"step": 5400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.0803398237041766,
|
| 424 |
+
"grad_norm": 20.03909683227539,
|
| 425 |
+
"learning_rate": 3.3080620050091385e-05,
|
| 426 |
+
"loss": 32.93142822265625,
|
| 427 |
+
"step": 5500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.0999828123849045,
|
| 431 |
+
"grad_norm": 19.49604606628418,
|
| 432 |
+
"learning_rate": 3.27421647600352e-05,
|
| 433 |
+
"loss": 32.9296630859375,
|
| 434 |
+
"step": 5600
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.1196258010656321,
|
| 438 |
+
"grad_norm": 21.259004592895508,
|
| 439 |
+
"learning_rate": 3.2403709469979017e-05,
|
| 440 |
+
"loss": 32.85189453125,
|
| 441 |
+
"step": 5700
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.1392687897463598,
|
| 445 |
+
"grad_norm": 19.597267150878906,
|
| 446 |
+
"learning_rate": 3.206525417992283e-05,
|
| 447 |
+
"loss": 32.82923583984375,
|
| 448 |
+
"step": 5800
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.1589117784270877,
|
| 452 |
+
"grad_norm": 20.224699020385742,
|
| 453 |
+
"learning_rate": 3.172679888986665e-05,
|
| 454 |
+
"loss": 32.7767626953125,
|
| 455 |
+
"step": 5900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.1785547671078154,
|
| 459 |
+
"grad_norm": 18.452495574951172,
|
| 460 |
+
"learning_rate": 3.138834359981047e-05,
|
| 461 |
+
"loss": 32.6592626953125,
|
| 462 |
+
"step": 6000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.1981977557885433,
|
| 466 |
+
"grad_norm": 19.971717834472656,
|
| 467 |
+
"learning_rate": 3.104988830975428e-05,
|
| 468 |
+
"loss": 32.80323974609375,
|
| 469 |
+
"step": 6100
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.217840744469271,
|
| 473 |
+
"grad_norm": 17.584882736206055,
|
| 474 |
+
"learning_rate": 3.07114330196981e-05,
|
| 475 |
+
"loss": 32.6551416015625,
|
| 476 |
+
"step": 6200
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.2374837331499988,
|
| 480 |
+
"grad_norm": 19.49502944946289,
|
| 481 |
+
"learning_rate": 3.0372977729641915e-05,
|
| 482 |
+
"loss": 32.73489990234375,
|
| 483 |
+
"step": 6300
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.2492695263584355,
|
| 487 |
+
"eval_loss": 3.9626989364624023,
|
| 488 |
+
"eval_runtime": 41.8921,
|
| 489 |
+
"eval_samples_per_second": 477.418,
|
| 490 |
+
"eval_steps_per_second": 14.919,
|
| 491 |
+
"step": 6360
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.2571267218307265,
|
| 495 |
+
"grad_norm": 20.214130401611328,
|
| 496 |
+
"learning_rate": 3.0034522439585734e-05,
|
| 497 |
+
"loss": 32.55817138671875,
|
| 498 |
+
"step": 6400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.2767697105114544,
|
| 502 |
+
"grad_norm": 20.668527603149414,
|
| 503 |
+
"learning_rate": 2.969606714952955e-05,
|
| 504 |
+
"loss": 32.53630615234375,
|
| 505 |
+
"step": 6500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.296412699192182,
|
| 509 |
+
"grad_norm": 18.479408264160156,
|
| 510 |
+
"learning_rate": 2.9357611859473366e-05,
|
| 511 |
+
"loss": 32.464462890625,
|
| 512 |
+
"step": 6600
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.31605568787291,
|
| 516 |
+
"grad_norm": 19.027793884277344,
|
| 517 |
+
"learning_rate": 2.9019156569417182e-05,
|
| 518 |
+
"loss": 32.48625244140625,
|
| 519 |
+
"step": 6700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.3356986765536376,
|
| 523 |
+
"grad_norm": 19.871105194091797,
|
| 524 |
+
"learning_rate": 2.8680701279361e-05,
|
| 525 |
+
"loss": 32.41595947265625,
|
| 526 |
+
"step": 6800
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.3553416652343655,
|
| 530 |
+
"grad_norm": 19.916994094848633,
|
| 531 |
+
"learning_rate": 2.8342245989304817e-05,
|
| 532 |
+
"loss": 32.11419921875,
|
| 533 |
+
"step": 6900
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.3749846539150932,
|
| 537 |
+
"grad_norm": 21.212909698486328,
|
| 538 |
+
"learning_rate": 2.8003790699248633e-05,
|
| 539 |
+
"loss": 32.30314453125,
|
| 540 |
+
"step": 7000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.3946276425958208,
|
| 544 |
+
"grad_norm": 25.216768264770508,
|
| 545 |
+
"learning_rate": 2.7665335409192445e-05,
|
| 546 |
+
"loss": 32.19344482421875,
|
| 547 |
+
"step": 7100
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.4142706312765487,
|
| 551 |
+
"grad_norm": 19.619844436645508,
|
| 552 |
+
"learning_rate": 2.732688011913626e-05,
|
| 553 |
+
"loss": 32.30953125,
|
| 554 |
+
"step": 7200
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.4339136199572766,
|
| 558 |
+
"grad_norm": 21.061376571655273,
|
| 559 |
+
"learning_rate": 2.6988424829080077e-05,
|
| 560 |
+
"loss": 32.3416162109375,
|
| 561 |
+
"step": 7300
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.4535566086380043,
|
| 565 |
+
"grad_norm": 18.674562454223633,
|
| 566 |
+
"learning_rate": 2.6649969539023896e-05,
|
| 567 |
+
"loss": 32.2662744140625,
|
| 568 |
+
"step": 7400
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.473199597318732,
|
| 572 |
+
"grad_norm": 18.776655197143555,
|
| 573 |
+
"learning_rate": 2.6311514248967712e-05,
|
| 574 |
+
"loss": 32.07302978515625,
|
| 575 |
+
"step": 7500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.4928425859994598,
|
| 579 |
+
"grad_norm": 19.0480899810791,
|
| 580 |
+
"learning_rate": 2.5973058958911528e-05,
|
| 581 |
+
"loss": 32.19434326171875,
|
| 582 |
+
"step": 7600
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.4991283423772928,
|
| 586 |
+
"eval_loss": 3.9200026988983154,
|
| 587 |
+
"eval_runtime": 42.1732,
|
| 588 |
+
"eval_samples_per_second": 474.235,
|
| 589 |
+
"eval_steps_per_second": 14.82,
|
| 590 |
+
"step": 7632
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.5124855746801877,
|
| 594 |
+
"grad_norm": 18.192241668701172,
|
| 595 |
+
"learning_rate": 2.5634603668855344e-05,
|
| 596 |
+
"loss": 32.0382470703125,
|
| 597 |
+
"step": 7700
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.5321285633609154,
|
| 601 |
+
"grad_norm": 21.64850425720215,
|
| 602 |
+
"learning_rate": 2.5296148378799163e-05,
|
| 603 |
+
"loss": 32.0071484375,
|
| 604 |
+
"step": 7800
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.551771552041643,
|
| 608 |
+
"grad_norm": 21.07256507873535,
|
| 609 |
+
"learning_rate": 2.495769308874298e-05,
|
| 610 |
+
"loss": 32.02736328125,
|
| 611 |
+
"step": 7900
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.5714145407223707,
|
| 615 |
+
"grad_norm": 18.811485290527344,
|
| 616 |
+
"learning_rate": 2.4619237798686794e-05,
|
| 617 |
+
"loss": 32.18232666015625,
|
| 618 |
+
"step": 8000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.5910575294030986,
|
| 622 |
+
"grad_norm": 20.226411819458008,
|
| 623 |
+
"learning_rate": 2.428078250863061e-05,
|
| 624 |
+
"loss": 31.81751220703125,
|
| 625 |
+
"step": 8100
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6107005180838265,
|
| 629 |
+
"grad_norm": 21.44918441772461,
|
| 630 |
+
"learning_rate": 2.394232721857443e-05,
|
| 631 |
+
"loss": 31.89043212890625,
|
| 632 |
+
"step": 8200
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.6303435067645542,
|
| 636 |
+
"grad_norm": 19.660367965698242,
|
| 637 |
+
"learning_rate": 2.3603871928518245e-05,
|
| 638 |
+
"loss": 31.95683349609375,
|
| 639 |
+
"step": 8300
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.6499864954452819,
|
| 643 |
+
"grad_norm": 19.144596099853516,
|
| 644 |
+
"learning_rate": 2.3265416638462058e-05,
|
| 645 |
+
"loss": 31.867197265625,
|
| 646 |
+
"step": 8400
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.6696294841260098,
|
| 650 |
+
"grad_norm": 18.604026794433594,
|
| 651 |
+
"learning_rate": 2.2926961348405877e-05,
|
| 652 |
+
"loss": 31.78265380859375,
|
| 653 |
+
"step": 8500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.6892724728067376,
|
| 657 |
+
"grad_norm": 19.978652954101562,
|
| 658 |
+
"learning_rate": 2.2588506058349693e-05,
|
| 659 |
+
"loss": 31.79925048828125,
|
| 660 |
+
"step": 8600
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.7089154614874653,
|
| 664 |
+
"grad_norm": 18.18141746520996,
|
| 665 |
+
"learning_rate": 2.225005076829351e-05,
|
| 666 |
+
"loss": 31.853974609375,
|
| 667 |
+
"step": 8700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.728558450168193,
|
| 671 |
+
"grad_norm": 17.99820899963379,
|
| 672 |
+
"learning_rate": 2.1911595478237325e-05,
|
| 673 |
+
"loss": 31.75265625,
|
| 674 |
+
"step": 8800
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.7482014388489209,
|
| 678 |
+
"grad_norm": 20.680606842041016,
|
| 679 |
+
"learning_rate": 2.1573140188181144e-05,
|
| 680 |
+
"loss": 31.6561328125,
|
| 681 |
+
"step": 8900
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.74898715839615,
|
| 685 |
+
"eval_loss": 3.863434076309204,
|
| 686 |
+
"eval_runtime": 42.0055,
|
| 687 |
+
"eval_samples_per_second": 476.128,
|
| 688 |
+
"eval_steps_per_second": 14.879,
|
| 689 |
+
"step": 8904
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.7678444275296488,
|
| 693 |
+
"grad_norm": 20.50802993774414,
|
| 694 |
+
"learning_rate": 2.123468489812496e-05,
|
| 695 |
+
"loss": 31.6072265625,
|
| 696 |
+
"step": 9000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.7874874162103764,
|
| 700 |
+
"grad_norm": 21.482328414916992,
|
| 701 |
+
"learning_rate": 2.0896229608068775e-05,
|
| 702 |
+
"loss": 31.7250537109375,
|
| 703 |
+
"step": 9100
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.807130404891104,
|
| 707 |
+
"grad_norm": 19.20509910583496,
|
| 708 |
+
"learning_rate": 2.055777431801259e-05,
|
| 709 |
+
"loss": 31.58796875,
|
| 710 |
+
"step": 9200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.826773393571832,
|
| 714 |
+
"grad_norm": 21.03694725036621,
|
| 715 |
+
"learning_rate": 2.0219319027956407e-05,
|
| 716 |
+
"loss": 31.68398193359375,
|
| 717 |
+
"step": 9300
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.8464163822525599,
|
| 721 |
+
"grad_norm": 18.272459030151367,
|
| 722 |
+
"learning_rate": 1.9880863737900223e-05,
|
| 723 |
+
"loss": 31.53086181640625,
|
| 724 |
+
"step": 9400
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.8660593709332876,
|
| 728 |
+
"grad_norm": 19.046916961669922,
|
| 729 |
+
"learning_rate": 1.9542408447844042e-05,
|
| 730 |
+
"loss": 31.525322265625,
|
| 731 |
+
"step": 9500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.8857023596140152,
|
| 735 |
+
"grad_norm": 21.118305206298828,
|
| 736 |
+
"learning_rate": 1.9203953157787858e-05,
|
| 737 |
+
"loss": 31.52841552734375,
|
| 738 |
+
"step": 9600
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.905345348294743,
|
| 742 |
+
"grad_norm": 18.861080169677734,
|
| 743 |
+
"learning_rate": 1.8865497867731674e-05,
|
| 744 |
+
"loss": 31.4529345703125,
|
| 745 |
+
"step": 9700
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.9249883369754708,
|
| 749 |
+
"grad_norm": 20.4729061126709,
|
| 750 |
+
"learning_rate": 1.852704257767549e-05,
|
| 751 |
+
"loss": 31.35305419921875,
|
| 752 |
+
"step": 9800
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.9446313256561987,
|
| 756 |
+
"grad_norm": 17.702392578125,
|
| 757 |
+
"learning_rate": 1.818858728761931e-05,
|
| 758 |
+
"loss": 31.5552734375,
|
| 759 |
+
"step": 9900
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.9642743143369263,
|
| 763 |
+
"grad_norm": 21.927942276000977,
|
| 764 |
+
"learning_rate": 1.785013199756312e-05,
|
| 765 |
+
"loss": 31.42951416015625,
|
| 766 |
+
"step": 10000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.983917303017654,
|
| 770 |
+
"grad_norm": 19.895252227783203,
|
| 771 |
+
"learning_rate": 1.7511676707506937e-05,
|
| 772 |
+
"loss": 31.416962890625,
|
| 773 |
+
"step": 10100
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.998845974415007,
|
| 777 |
+
"eval_loss": 3.819389820098877,
|
| 778 |
+
"eval_runtime": 41.9176,
|
| 779 |
+
"eval_samples_per_second": 477.126,
|
| 780 |
+
"eval_steps_per_second": 14.91,
|
| 781 |
+
"step": 10176
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.003535737962531,
|
| 785 |
+
"grad_norm": 20.209577560424805,
|
| 786 |
+
"learning_rate": 1.7173221417450756e-05,
|
| 787 |
+
"loss": 31.25757568359375,
|
| 788 |
+
"step": 10200
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.0231787266432586,
|
| 792 |
+
"grad_norm": 19.49869155883789,
|
| 793 |
+
"learning_rate": 1.6834766127394572e-05,
|
| 794 |
+
"loss": 31.14395263671875,
|
| 795 |
+
"step": 10300
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.0428217153239867,
|
| 799 |
+
"grad_norm": 20.60426139831543,
|
| 800 |
+
"learning_rate": 1.6496310837338388e-05,
|
| 801 |
+
"loss": 31.38017333984375,
|
| 802 |
+
"step": 10400
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.0624647040047144,
|
| 806 |
+
"grad_norm": 19.177818298339844,
|
| 807 |
+
"learning_rate": 1.6157855547282204e-05,
|
| 808 |
+
"loss": 31.20944091796875,
|
| 809 |
+
"step": 10500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.082107692685442,
|
| 813 |
+
"grad_norm": 20.949337005615234,
|
| 814 |
+
"learning_rate": 1.5819400257226023e-05,
|
| 815 |
+
"loss": 31.2146240234375,
|
| 816 |
+
"step": 10600
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.1017506813661697,
|
| 820 |
+
"grad_norm": 19.25591468811035,
|
| 821 |
+
"learning_rate": 1.548094496716984e-05,
|
| 822 |
+
"loss": 31.202607421875,
|
| 823 |
+
"step": 10700
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.121393670046898,
|
| 827 |
+
"grad_norm": 18.960092544555664,
|
| 828 |
+
"learning_rate": 1.5142489677113653e-05,
|
| 829 |
+
"loss": 31.14611572265625,
|
| 830 |
+
"step": 10800
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.1410366587276255,
|
| 834 |
+
"grad_norm": 18.479068756103516,
|
| 835 |
+
"learning_rate": 1.4804034387057469e-05,
|
| 836 |
+
"loss": 31.26153564453125,
|
| 837 |
+
"step": 10900
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.160679647408353,
|
| 841 |
+
"grad_norm": 21.587387084960938,
|
| 842 |
+
"learning_rate": 1.4465579097001287e-05,
|
| 843 |
+
"loss": 31.1222998046875,
|
| 844 |
+
"step": 11000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.180322636089081,
|
| 848 |
+
"grad_norm": 17.947052001953125,
|
| 849 |
+
"learning_rate": 1.4127123806945102e-05,
|
| 850 |
+
"loss": 31.08917236328125,
|
| 851 |
+
"step": 11100
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.199965624769809,
|
| 855 |
+
"grad_norm": 19.169307708740234,
|
| 856 |
+
"learning_rate": 1.378866851688892e-05,
|
| 857 |
+
"loss": 31.0661474609375,
|
| 858 |
+
"step": 11200
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.2196086134505366,
|
| 862 |
+
"grad_norm": 16.882522583007812,
|
| 863 |
+
"learning_rate": 1.3450213226832736e-05,
|
| 864 |
+
"loss": 30.9886328125,
|
| 865 |
+
"step": 11300
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.2392516021312643,
|
| 869 |
+
"grad_norm": 19.624177932739258,
|
| 870 |
+
"learning_rate": 1.3111757936776553e-05,
|
| 871 |
+
"loss": 30.93468505859375,
|
| 872 |
+
"step": 11400
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.2486802366980134,
|
| 876 |
+
"eval_loss": 3.786958694458008,
|
| 877 |
+
"eval_runtime": 41.8524,
|
| 878 |
+
"eval_samples_per_second": 477.869,
|
| 879 |
+
"eval_steps_per_second": 14.933,
|
| 880 |
+
"step": 11448
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.258894590811992,
|
| 884 |
+
"grad_norm": 20.477542877197266,
|
| 885 |
+
"learning_rate": 1.2773302646720369e-05,
|
| 886 |
+
"loss": 31.00721923828125,
|
| 887 |
+
"step": 11500
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.2785375794927196,
|
| 891 |
+
"grad_norm": 19.928098678588867,
|
| 892 |
+
"learning_rate": 1.2434847356664185e-05,
|
| 893 |
+
"loss": 30.95269775390625,
|
| 894 |
+
"step": 11600
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.2981805681734477,
|
| 898 |
+
"grad_norm": 19.002788543701172,
|
| 899 |
+
"learning_rate": 1.2096392066608003e-05,
|
| 900 |
+
"loss": 30.908701171875,
|
| 901 |
+
"step": 11700
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.3178235568541754,
|
| 905 |
+
"grad_norm": 20.50242805480957,
|
| 906 |
+
"learning_rate": 1.1757936776551818e-05,
|
| 907 |
+
"loss": 30.96546142578125,
|
| 908 |
+
"step": 11800
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.337466545534903,
|
| 912 |
+
"grad_norm": 20.48063850402832,
|
| 913 |
+
"learning_rate": 1.1419481486495634e-05,
|
| 914 |
+
"loss": 30.9563623046875,
|
| 915 |
+
"step": 11900
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.3571095342156307,
|
| 919 |
+
"grad_norm": 19.522266387939453,
|
| 920 |
+
"learning_rate": 1.108102619643945e-05,
|
| 921 |
+
"loss": 30.85960205078125,
|
| 922 |
+
"step": 12000
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.376752522896359,
|
| 926 |
+
"grad_norm": 21.33004379272461,
|
| 927 |
+
"learning_rate": 1.0742570906383268e-05,
|
| 928 |
+
"loss": 30.829111328125,
|
| 929 |
+
"step": 12100
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.3963955115770865,
|
| 933 |
+
"grad_norm": 20.311534881591797,
|
| 934 |
+
"learning_rate": 1.0404115616327083e-05,
|
| 935 |
+
"loss": 30.93859619140625,
|
| 936 |
+
"step": 12200
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.416038500257814,
|
| 940 |
+
"grad_norm": 20.128795623779297,
|
| 941 |
+
"learning_rate": 1.00656603262709e-05,
|
| 942 |
+
"loss": 30.750810546875,
|
| 943 |
+
"step": 12300
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.435681488938542,
|
| 947 |
+
"grad_norm": 22.28921890258789,
|
| 948 |
+
"learning_rate": 9.727205036214717e-06,
|
| 949 |
+
"loss": 30.714560546875,
|
| 950 |
+
"step": 12400
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.4553244776192695,
|
| 954 |
+
"grad_norm": 24.13454818725586,
|
| 955 |
+
"learning_rate": 9.388749746158533e-06,
|
| 956 |
+
"loss": 30.87623779296875,
|
| 957 |
+
"step": 12500
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.4749674662999976,
|
| 961 |
+
"grad_norm": 20.58381462097168,
|
| 962 |
+
"learning_rate": 9.05029445610235e-06,
|
| 963 |
+
"loss": 30.60492431640625,
|
| 964 |
+
"step": 12600
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.4946104549807253,
|
| 968 |
+
"grad_norm": 20.045475006103516,
|
| 969 |
+
"learning_rate": 8.711839166046164e-06,
|
| 970 |
+
"loss": 30.8008154296875,
|
| 971 |
+
"step": 12700
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.498539052716871,
|
| 975 |
+
"eval_loss": 3.7586019039154053,
|
| 976 |
+
"eval_runtime": 42.0034,
|
| 977 |
+
"eval_samples_per_second": 476.152,
|
| 978 |
+
"eval_steps_per_second": 14.88,
|
| 979 |
+
"step": 12720
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 2.514253443661453,
|
| 983 |
+
"grad_norm": 19.53034210205078,
|
| 984 |
+
"learning_rate": 8.373383875989982e-06,
|
| 985 |
+
"loss": 30.7534326171875,
|
| 986 |
+
"step": 12800
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.533896432342181,
|
| 990 |
+
"grad_norm": 20.510520935058594,
|
| 991 |
+
"learning_rate": 8.0349285859338e-06,
|
| 992 |
+
"loss": 30.7755859375,
|
| 993 |
+
"step": 12900
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.5535394210229088,
|
| 997 |
+
"grad_norm": 20.725147247314453,
|
| 998 |
+
"learning_rate": 7.696473295877615e-06,
|
| 999 |
+
"loss": 30.9005029296875,
|
| 1000 |
+
"step": 13000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.5731824097036364,
|
| 1004 |
+
"grad_norm": 20.11240577697754,
|
| 1005 |
+
"learning_rate": 7.358018005821431e-06,
|
| 1006 |
+
"loss": 30.81609130859375,
|
| 1007 |
+
"step": 13100
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 2.592825398384364,
|
| 1011 |
+
"grad_norm": 19.01041603088379,
|
| 1012 |
+
"learning_rate": 7.019562715765248e-06,
|
| 1013 |
+
"loss": 30.70421142578125,
|
| 1014 |
+
"step": 13200
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.6124683870650918,
|
| 1018 |
+
"grad_norm": 20.232532501220703,
|
| 1019 |
+
"learning_rate": 6.681107425709064e-06,
|
| 1020 |
+
"loss": 30.7105322265625,
|
| 1021 |
+
"step": 13300
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.63211137574582,
|
| 1025 |
+
"grad_norm": 21.33913803100586,
|
| 1026 |
+
"learning_rate": 6.342652135652881e-06,
|
| 1027 |
+
"loss": 30.76764892578125,
|
| 1028 |
+
"step": 13400
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.6517543644265475,
|
| 1032 |
+
"grad_norm": 19.718833923339844,
|
| 1033 |
+
"learning_rate": 6.004196845596697e-06,
|
| 1034 |
+
"loss": 30.75705078125,
|
| 1035 |
+
"step": 13500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.671397353107275,
|
| 1039 |
+
"grad_norm": 20.983705520629883,
|
| 1040 |
+
"learning_rate": 5.665741555540514e-06,
|
| 1041 |
+
"loss": 30.66492431640625,
|
| 1042 |
+
"step": 13600
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 2.691040341788003,
|
| 1046 |
+
"grad_norm": 18.726970672607422,
|
| 1047 |
+
"learning_rate": 5.3272862654843295e-06,
|
| 1048 |
+
"loss": 30.72262451171875,
|
| 1049 |
+
"step": 13700
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.710683330468731,
|
| 1053 |
+
"grad_norm": 21.197751998901367,
|
| 1054 |
+
"learning_rate": 4.988830975428146e-06,
|
| 1055 |
+
"loss": 30.6771728515625,
|
| 1056 |
+
"step": 13800
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 2.7303263191494587,
|
| 1060 |
+
"grad_norm": 21.318998336791992,
|
| 1061 |
+
"learning_rate": 4.650375685371963e-06,
|
| 1062 |
+
"loss": 30.52608642578125,
|
| 1063 |
+
"step": 13900
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 2.748397868735728,
|
| 1067 |
+
"eval_loss": 3.7217817306518555,
|
| 1068 |
+
"eval_runtime": 41.8977,
|
| 1069 |
+
"eval_samples_per_second": 477.353,
|
| 1070 |
+
"eval_steps_per_second": 14.917,
|
| 1071 |
+
"step": 13992
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 2.7499693078301863,
|
| 1075 |
+
"grad_norm": 19.221782684326172,
|
| 1076 |
+
"learning_rate": 4.3119203953157795e-06,
|
| 1077 |
+
"loss": 30.623740234375,
|
| 1078 |
+
"step": 14000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 2.769612296510914,
|
| 1082 |
+
"grad_norm": 17.869342803955078,
|
| 1083 |
+
"learning_rate": 3.973465105259595e-06,
|
| 1084 |
+
"loss": 30.61525634765625,
|
| 1085 |
+
"step": 14100
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 2.7892552851916417,
|
| 1089 |
+
"grad_norm": 18.45319938659668,
|
| 1090 |
+
"learning_rate": 3.635009815203412e-06,
|
| 1091 |
+
"loss": 30.6033154296875,
|
| 1092 |
+
"step": 14200
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 2.80889827387237,
|
| 1096 |
+
"grad_norm": 18.811376571655273,
|
| 1097 |
+
"learning_rate": 3.296554525147228e-06,
|
| 1098 |
+
"loss": 30.6585498046875,
|
| 1099 |
+
"step": 14300
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 2.8285412625530975,
|
| 1103 |
+
"grad_norm": 19.703887939453125,
|
| 1104 |
+
"learning_rate": 2.9580992350910446e-06,
|
| 1105 |
+
"loss": 30.57553955078125,
|
| 1106 |
+
"step": 14400
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.848184251233825,
|
| 1110 |
+
"grad_norm": 19.73227882385254,
|
| 1111 |
+
"learning_rate": 2.619643945034861e-06,
|
| 1112 |
+
"loss": 30.6737548828125,
|
| 1113 |
+
"step": 14500
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.8678272399145532,
|
| 1117 |
+
"grad_norm": 20.356998443603516,
|
| 1118 |
+
"learning_rate": 2.281188654978677e-06,
|
| 1119 |
+
"loss": 30.6970361328125,
|
| 1120 |
+
"step": 14600
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 2.887470228595281,
|
| 1124 |
+
"grad_norm": 21.043643951416016,
|
| 1125 |
+
"learning_rate": 1.942733364922494e-06,
|
| 1126 |
+
"loss": 30.5473388671875,
|
| 1127 |
+
"step": 14700
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.9071132172760086,
|
| 1131 |
+
"grad_norm": 18.5972843170166,
|
| 1132 |
+
"learning_rate": 1.6042780748663105e-06,
|
| 1133 |
+
"loss": 30.6621875,
|
| 1134 |
+
"step": 14800
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.9267562059567362,
|
| 1138 |
+
"grad_norm": 19.071395874023438,
|
| 1139 |
+
"learning_rate": 1.2658227848101265e-06,
|
| 1140 |
+
"loss": 30.491064453125,
|
| 1141 |
+
"step": 14900
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.946399194637464,
|
| 1145 |
+
"grad_norm": 19.5911808013916,
|
| 1146 |
+
"learning_rate": 9.27367494753943e-07,
|
| 1147 |
+
"loss": 30.54241455078125,
|
| 1148 |
+
"step": 15000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.966042183318192,
|
| 1152 |
+
"grad_norm": 21.04094696044922,
|
| 1153 |
+
"learning_rate": 5.889122046977595e-07,
|
| 1154 |
+
"loss": 30.4769384765625,
|
| 1155 |
+
"step": 15100
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.9856851719989197,
|
| 1159 |
+
"grad_norm": 18.463882446289062,
|
| 1160 |
+
"learning_rate": 2.5045691464157585e-07,
|
| 1161 |
+
"loss": 30.60388916015625,
|
| 1162 |
+
"step": 15200
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.9982566847545855,
|
| 1166 |
+
"eval_loss": 3.722125291824341,
|
| 1167 |
+
"eval_runtime": 42.0954,
|
| 1168 |
+
"eval_samples_per_second": 475.111,
|
| 1169 |
+
"eval_steps_per_second": 14.847,
|
| 1170 |
+
"step": 15264
|
| 1171 |
+
}
|
| 1172 |
+
],
|
| 1173 |
+
"logging_steps": 100,
|
| 1174 |
+
"max_steps": 15273,
|
| 1175 |
+
"num_input_tokens_seen": 0,
|
| 1176 |
+
"num_train_epochs": 3,
|
| 1177 |
+
"save_steps": 1272,
|
| 1178 |
+
"stateful_callbacks": {
|
| 1179 |
+
"TrainerControl": {
|
| 1180 |
+
"args": {
|
| 1181 |
+
"should_epoch_stop": false,
|
| 1182 |
+
"should_evaluate": false,
|
| 1183 |
+
"should_log": false,
|
| 1184 |
+
"should_save": true,
|
| 1185 |
+
"should_training_stop": true
|
| 1186 |
+
},
|
| 1187 |
+
"attributes": {}
|
| 1188 |
+
}
|
| 1189 |
+
},
|
| 1190 |
+
"total_flos": 1.0290819911189391e+18,
|
| 1191 |
+
"train_batch_size": 32,
|
| 1192 |
+
"trial_name": null,
|
| 1193 |
+
"trial_params": null
|
| 1194 |
+
}
|
checkpoint-15273/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaec524752280134c2e0387d7f5f1e2cc6d34eaa3f289327a642e9b1d7d2b9c9
|
| 3 |
+
size 5137
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:792f46cb1378b8ab1a168296ccf3cff6636948e4023ba6f87849d3969770c012
|
| 3 |
+
size 442633860
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5137
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaec524752280134c2e0387d7f5f1e2cc6d34eaa3f289327a642e9b1d7d2b9c9
|
| 3 |
size 5137
|