Hugging Face's logo

Azrail
/
smallm_70

Text Generation
Transformers
Safetensors
English
smallm
transformer
language-model
experimental
conversational
custom_code
Model card Files
xet
 Community
Azrail commited on
Commit
4be7a9a
·
verified ·
1 Parent(s): 6d2707e

Training in progress, step 29000, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +182 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6bfbf59e48ccbe1c689774152a90d74c704789cf0a24340e31d970e2ae2f82b
3
  size 301235464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed58b9377855fe80a778b09bc2f72a0dc4e91c0242adc79b95ac4868b0921df
3
  size 301235464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bf459077dbfc45a1bef121401b69108c6a04f583daf68be560ffcfd374476dc
3
  size 602335994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd09749daae0bf1f567d4c6a6fbe152fdcd1c8cc6de8109ecaa45912c30be9b2
3
  size 602335994
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed11a30b4dd7817e80835c6ecf6fe24d8d86f18c493af4a03052d58b7baf6875
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9846b22739edf9c19756d28d9b1bb6ad70ad314d431493efdbec089d6aa54593
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06d5fef101c9d39d51795e2426ebd97ece14c40eab5611cbd021ffd2d11b16ce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6038c3966e5acd5e329cd1d75f036dea625d34bb913a8f0d05452e8d1784e0ba
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.1335607045327164,
6
  "eval_steps": 500,
7
- "global_step": 28000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4992,11 +4992,189 @@
4992
  "eval_steps_per_second": 24.85,
4993
  "num_input_tokens_seen": 7340032000,
4994
  "step": 28000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4995
  }
4996
  ],
4997
  "logging_steps": 50,
4998
  "max_steps": 70000,
4999
- "num_input_tokens_seen": 7340032000,
5000
  "num_train_epochs": 1,
5001
  "save_steps": 1000,
5002
  "stateful_callbacks": {
@@ -5011,7 +5189,7 @@
5011
  "attributes": {}
5012
  }
5013
  },
5014
- "total_flos": 1.96353019871232e+18,
5015
  "train_batch_size": 64,
5016
  "trial_name": null,
5017
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.13833072969459914,
6
  "eval_steps": 500,
7
+ "global_step": 29000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4992
  "eval_steps_per_second": 24.85,
4993
  "num_input_tokens_seen": 7340032000,
4994
  "step": 28000
4995
+ },
4996
+ {
4997
+ "epoch": 0.13379920579081056,
4998
+ "grad_norm": 0.19409704208374023,
4999
+ "learning_rate": 0.001,
5000
+ "loss": 2.6776,
5001
+ "num_input_tokens_seen": 7353139200,
5002
+ "step": 28050
5003
+ },
5004
+ {
5005
+ "epoch": 0.1340377070489047,
5006
+ "grad_norm": 0.1712968647480011,
5007
+ "learning_rate": 0.001,
5008
+ "loss": 2.6679,
5009
+ "num_input_tokens_seen": 7366246400,
5010
+ "step": 28100
5011
+ },
5012
+ {
5013
+ "epoch": 0.13427620830699882,
5014
+ "grad_norm": 0.20586130023002625,
5015
+ "learning_rate": 0.001,
5016
+ "loss": 2.6633,
5017
+ "num_input_tokens_seen": 7379353600,
5018
+ "step": 28150
5019
+ },
5020
+ {
5021
+ "epoch": 0.13451470956509295,
5022
+ "grad_norm": 0.1776891052722931,
5023
+ "learning_rate": 0.001,
5024
+ "loss": 2.6683,
5025
+ "num_input_tokens_seen": 7392460800,
5026
+ "step": 28200
5027
+ },
5028
+ {
5029
+ "epoch": 0.1347532108231871,
5030
+ "grad_norm": 0.19293451309204102,
5031
+ "learning_rate": 0.001,
5032
+ "loss": 2.6645,
5033
+ "num_input_tokens_seen": 7405568000,
5034
+ "step": 28250
5035
+ },
5036
+ {
5037
+ "epoch": 0.13499171208128122,
5038
+ "grad_norm": 0.17754724621772766,
5039
+ "learning_rate": 0.001,
5040
+ "loss": 2.6685,
5041
+ "num_input_tokens_seen": 7418675200,
5042
+ "step": 28300
5043
+ },
5044
+ {
5045
+ "epoch": 0.13523021333937538,
5046
+ "grad_norm": 0.17739038169384003,
5047
+ "learning_rate": 0.001,
5048
+ "loss": 2.6607,
5049
+ "num_input_tokens_seen": 7431782400,
5050
+ "step": 28350
5051
+ },
5052
+ {
5053
+ "epoch": 0.1354687145974695,
5054
+ "grad_norm": 0.175009086728096,
5055
+ "learning_rate": 0.001,
5056
+ "loss": 2.6679,
5057
+ "num_input_tokens_seen": 7444889600,
5058
+ "step": 28400
5059
+ },
5060
+ {
5061
+ "epoch": 0.13570721585556364,
5062
+ "grad_norm": 0.2229124754667282,
5063
+ "learning_rate": 0.001,
5064
+ "loss": 2.6687,
5065
+ "num_input_tokens_seen": 7457996800,
5066
+ "step": 28450
5067
+ },
5068
+ {
5069
+ "epoch": 0.13594571711365777,
5070
+ "grad_norm": 0.1791590005159378,
5071
+ "learning_rate": 0.001,
5072
+ "loss": 2.6741,
5073
+ "num_input_tokens_seen": 7471104000,
5074
+ "step": 28500
5075
+ },
5076
+ {
5077
+ "epoch": 0.13594571711365777,
5078
+ "eval_loss": 2.5456056594848633,
5079
+ "eval_runtime": 50.6342,
5080
+ "eval_samples_per_second": 98.747,
5081
+ "eval_steps_per_second": 24.687,
5082
+ "num_input_tokens_seen": 7471104000,
5083
+ "step": 28500
5084
+ },
5085
+ {
5086
+ "epoch": 0.1361842183717519,
5087
+ "grad_norm": 0.18920041620731354,
5088
+ "learning_rate": 0.001,
5089
+ "loss": 2.6612,
5090
+ "num_input_tokens_seen": 7484211200,
5091
+ "step": 28550
5092
+ },
5093
+ {
5094
+ "epoch": 0.13642271962984603,
5095
+ "grad_norm": 0.19247522950172424,
5096
+ "learning_rate": 0.001,
5097
+ "loss": 2.6597,
5098
+ "num_input_tokens_seen": 7497318400,
5099
+ "step": 28600
5100
+ },
5101
+ {
5102
+ "epoch": 0.1366612208879402,
5103
+ "grad_norm": 0.22499197721481323,
5104
+ "learning_rate": 0.001,
5105
+ "loss": 2.6583,
5106
+ "num_input_tokens_seen": 7510425600,
5107
+ "step": 28650
5108
+ },
5109
+ {
5110
+ "epoch": 0.13689972214603432,
5111
+ "grad_norm": 0.18946559727191925,
5112
+ "learning_rate": 0.001,
5113
+ "loss": 2.6612,
5114
+ "num_input_tokens_seen": 7523532800,
5115
+ "step": 28700
5116
+ },
5117
+ {
5118
+ "epoch": 0.13713822340412846,
5119
+ "grad_norm": 0.19621454179286957,
5120
+ "learning_rate": 0.001,
5121
+ "loss": 2.6425,
5122
+ "num_input_tokens_seen": 7536640000,
5123
+ "step": 28750
5124
+ },
5125
+ {
5126
+ "epoch": 0.1373767246622226,
5127
+ "grad_norm": 0.21594376862049103,
5128
+ "learning_rate": 0.001,
5129
+ "loss": 2.6564,
5130
+ "num_input_tokens_seen": 7549747200,
5131
+ "step": 28800
5132
+ },
5133
+ {
5134
+ "epoch": 0.13761522592031672,
5135
+ "grad_norm": 0.18186470866203308,
5136
+ "learning_rate": 0.001,
5137
+ "loss": 2.6728,
5138
+ "num_input_tokens_seen": 7562854400,
5139
+ "step": 28850
5140
+ },
5141
+ {
5142
+ "epoch": 0.13785372717841088,
5143
+ "grad_norm": 0.19369743764400482,
5144
+ "learning_rate": 0.001,
5145
+ "loss": 2.6585,
5146
+ "num_input_tokens_seen": 7575961600,
5147
+ "step": 28900
5148
+ },
5149
+ {
5150
+ "epoch": 0.138092228436505,
5151
+ "grad_norm": 0.1897999793291092,
5152
+ "learning_rate": 0.001,
5153
+ "loss": 2.6564,
5154
+ "num_input_tokens_seen": 7589068800,
5155
+ "step": 28950
5156
+ },
5157
+ {
5158
+ "epoch": 0.13833072969459914,
5159
+ "grad_norm": 0.18076784908771515,
5160
+ "learning_rate": 0.001,
5161
+ "loss": 2.6453,
5162
+ "num_input_tokens_seen": 7602176000,
5163
+ "step": 29000
5164
+ },
5165
+ {
5166
+ "epoch": 0.13833072969459914,
5167
+ "eval_loss": 2.54413104057312,
5168
+ "eval_runtime": 50.9152,
5169
+ "eval_samples_per_second": 98.202,
5170
+ "eval_steps_per_second": 24.551,
5171
+ "num_input_tokens_seen": 7602176000,
5172
+ "step": 29000
5173
  }
5174
  ],
5175
  "logging_steps": 50,
5176
  "max_steps": 70000,
5177
+ "num_input_tokens_seen": 7602176000,
5178
  "num_train_epochs": 1,
5179
  "save_steps": 1000,
5180
  "stateful_callbacks": {
 
5189
  "attributes": {}
5190
  }
5191
  },
5192
+ "total_flos": 2.03365627723776e+18,
5193
  "train_batch_size": 64,
5194
  "trial_name": null,
5195
  "trial_params": null