Francesco0101 commited on
Commit
9b4fde6
1 Parent(s): 24c592e

Training in progress, epoch 6

Browse files
last-checkpoint/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Francesco0101/FRABERT-distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6f13d3f381449f8d84b7ca05fb821a8b2c0861629beaa791e6c2b5fc00bbb5d
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172a879e54f0613ed34fc2ebe311f2f27a68a3f88d233f7000673e5598a77685
3
  size 267835644
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9765040586104af3a74cdbea9cc7074b0e48ef0d1226c3c15c17be1de83b9f59
3
  size 535733434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0385300931157697e4a915b5ce3364c3ef452b5cc6f19883fa9a9bcbdfdaf3b4
3
  size 535733434
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:675b9a4f8cd0e254dcba3b5459763afcac5d970080440d891cee0ad59e24dfb1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b2cbbcfce68a465b5dc9649714636223f26c4334afe4a2b30c904f877d83a7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74a0adf096c9eebfe9a2fa6c4d4fa6dd5ed912c3085653d4e028c18b90b90dc0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2410c1bb6e04ddda81f1a5814723f61652cb286cac246e7b64a7b46322f8b053
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.6361710372570955,
3
  "best_model_checkpoint": "training_dir/checkpoint-250",
4
- "epoch": 5.0,
5
  "eval_steps": 500,
6
- "global_step": 625,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -64,50 +64,12 @@
64
  "eval_samples_per_second": 79.297,
65
  "eval_steps_per_second": 9.912,
66
  "step": 375
67
- },
68
- {
69
- "epoch": 4.0,
70
- "grad_norm": 27.72207260131836,
71
- "learning_rate": 0.0001,
72
- "loss": 0.2795,
73
- "step": 500
74
- },
75
- {
76
- "epoch": 4.0,
77
- "eval_accuracy": 0.611451048951049,
78
- "eval_f1": 0.5839059582567918,
79
- "eval_loss": 1.4940129518508911,
80
- "eval_precision": 0.6264845385709801,
81
- "eval_recall": 0.611451048951049,
82
- "eval_runtime": 26.4977,
83
- "eval_samples_per_second": 86.347,
84
- "eval_steps_per_second": 10.793,
85
- "step": 500
86
- },
87
- {
88
- "epoch": 5.0,
89
- "grad_norm": 7.975765705108643,
90
- "learning_rate": 5e-05,
91
- "loss": 0.2239,
92
- "step": 625
93
- },
94
- {
95
- "epoch": 5.0,
96
- "eval_accuracy": 0.6324300699300699,
97
- "eval_f1": 0.6186338450685905,
98
- "eval_loss": 1.4131898880004883,
99
- "eval_precision": 0.657121853967928,
100
- "eval_recall": 0.6324300699300699,
101
- "eval_runtime": 26.1975,
102
- "eval_samples_per_second": 87.337,
103
- "eval_steps_per_second": 10.917,
104
- "step": 625
105
  }
106
  ],
107
  "logging_steps": 500,
108
- "max_steps": 750,
109
  "num_input_tokens_seen": 0,
110
- "num_train_epochs": 6,
111
  "save_steps": 500,
112
  "stateful_callbacks": {
113
  "TrainerControl": {
@@ -116,12 +78,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1019396207880000.0,
125
  "train_batch_size": 16,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": 0.6361710372570955,
3
  "best_model_checkpoint": "training_dir/checkpoint-250",
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 375,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
64
  "eval_samples_per_second": 79.297,
65
  "eval_steps_per_second": 9.912,
66
  "step": 375
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  }
68
  ],
69
  "logging_steps": 500,
70
+ "max_steps": 375,
71
  "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 3,
73
  "save_steps": 500,
74
  "stateful_callbacks": {
75
  "TrainerControl": {
 
78
  "should_evaluate": false,
79
  "should_log": false,
80
  "should_save": true,
81
+ "should_training_stop": true
82
  },
83
  "attributes": {}
84
  }
85
  },
86
+ "total_flos": 611637724728000.0,
87
  "train_batch_size": 16,
88
  "trial_name": null,
89
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc57af78e6fe472d6ff8fcdc48d3f980e6db66111852185ec17fc1a8cd98a77e
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e12f88c03a5bd8b8e87382f55cb509de4b19cb32f104c0c58580a43586af693
3
  size 5176
logs/events.out.tfevents.1720281621.f0fb2462ada0.270.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c44d242550e9828d81b1316b28c057a3444f48ea3cc31a0d98762a952be26772
3
- size 6326
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9dbf90786cb995fdc4233c741cbc8afc1f1fe3908b8ef0c2256fd17d111893
3
+ size 7363
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6f13d3f381449f8d84b7ca05fb821a8b2c0861629beaa791e6c2b5fc00bbb5d
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efcd7c63e38a38d3550783e6dfd87fe60211e00634586d614cfc77ba08c94ada
3
  size 267835644