Hugging Face's logo

HealthTeam
/
mt5-small-finetuned-MultiHead-230207

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
HealthTeam commited on
Commit
c032c2b
•
1 Parent(s): 70ed69b

Training in progress, step 176768

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +135 -3
  6. pytorch_model.bin +1 -1
  7. runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d74fdb539d44a35348b6810c0d848c4bf56592bd5cf768ed81575f1ebb8bcb14
3
  size 2401461637
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab7c11e32bc742d74bdc97f13f6eba893be4230d872eaecd0689a72f1fc3083
3
  size 2401461637
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a5ec2ac5d923b5dd8a99ca581137ee6c85b4ea12bee1568d23a8455d2a58084
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2991727b803e8a0b02542f03f6557f0258a9e36d172bbf826844685e5c5185
3
  size 1200739717
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510fc81178791ae60890b99ad1e29739b0a1957018583076b8ffe9ee3580c1d3
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fc5cf4ee407f42d02567591ae73b57604321015aed2152689ffa91a768c5cd
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d8dac73ce104ca44387089f603547c06c75d1a306882323278557a38f3d277f
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c9fc3a1a25e64cc5d7eeddd2fe8bdbd04e891f66624bb894c6a839cce384bc5
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.4652643479813157,
5
- "global_step": 165720,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -2010,11 +2010,143 @@
2010
  "learning_rate": 3.5867226007358706e-06,
2011
  "loss": 2.7724,
2012
  "step": 165500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2013
  }
2014
  ],
2015
  "max_steps": 201666,
2016
  "num_train_epochs": 3,
2017
- "total_flos": 1.9488674798095565e+17,
2018
  "trial_name": null,
2019
  "trial_params": null
2020
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.629615304513403,
5
+ "global_step": 176768,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
2010
  "learning_rate": 3.5867226007358706e-06,
2011
  "loss": 2.7724,
2012
  "step": 165500
2013
+ },
2014
+ {
2015
+ "epoch": 2.47,
2016
+ "learning_rate": 3.537135659952595e-06,
2017
+ "loss": 2.7647,
2018
+ "step": 166000
2019
+ },
2020
+ {
2021
+ "epoch": 2.48,
2022
+ "learning_rate": 3.4875487191693196e-06,
2023
+ "loss": 2.7719,
2024
+ "step": 166500
2025
+ },
2026
+ {
2027
+ "epoch": 2.48,
2028
+ "learning_rate": 3.4379617783860446e-06,
2029
+ "loss": 2.7578,
2030
+ "step": 167000
2031
+ },
2032
+ {
2033
+ "epoch": 2.49,
2034
+ "learning_rate": 3.388374837602769e-06,
2035
+ "loss": 2.7478,
2036
+ "step": 167500
2037
+ },
2038
+ {
2039
+ "epoch": 2.5,
2040
+ "learning_rate": 3.3387878968194936e-06,
2041
+ "loss": 2.7747,
2042
+ "step": 168000
2043
+ },
2044
+ {
2045
+ "epoch": 2.51,
2046
+ "learning_rate": 3.2892009560362186e-06,
2047
+ "loss": 2.7533,
2048
+ "step": 168500
2049
+ },
2050
+ {
2051
+ "epoch": 2.51,
2052
+ "learning_rate": 3.239614015252943e-06,
2053
+ "loss": 2.7488,
2054
+ "step": 169000
2055
+ },
2056
+ {
2057
+ "epoch": 2.52,
2058
+ "learning_rate": 3.190027074469668e-06,
2059
+ "loss": 2.7577,
2060
+ "step": 169500
2061
+ },
2062
+ {
2063
+ "epoch": 2.53,
2064
+ "learning_rate": 3.1404401336863925e-06,
2065
+ "loss": 2.7646,
2066
+ "step": 170000
2067
+ },
2068
+ {
2069
+ "epoch": 2.54,
2070
+ "learning_rate": 3.090853192903117e-06,
2071
+ "loss": 2.7556,
2072
+ "step": 170500
2073
+ },
2074
+ {
2075
+ "epoch": 2.54,
2076
+ "learning_rate": 3.041266252119842e-06,
2077
+ "loss": 2.7578,
2078
+ "step": 171000
2079
+ },
2080
+ {
2081
+ "epoch": 2.55,
2082
+ "learning_rate": 2.9916793113365665e-06,
2083
+ "loss": 2.7428,
2084
+ "step": 171500
2085
+ },
2086
+ {
2087
+ "epoch": 2.56,
2088
+ "learning_rate": 2.942092370553291e-06,
2089
+ "loss": 2.7487,
2090
+ "step": 172000
2091
+ },
2092
+ {
2093
+ "epoch": 2.57,
2094
+ "learning_rate": 2.892505429770016e-06,
2095
+ "loss": 2.7457,
2096
+ "step": 172500
2097
+ },
2098
+ {
2099
+ "epoch": 2.57,
2100
+ "learning_rate": 2.8429184889867405e-06,
2101
+ "loss": 2.7366,
2102
+ "step": 173000
2103
+ },
2104
+ {
2105
+ "epoch": 2.58,
2106
+ "learning_rate": 2.7933315482034655e-06,
2107
+ "loss": 2.7497,
2108
+ "step": 173500
2109
+ },
2110
+ {
2111
+ "epoch": 2.59,
2112
+ "learning_rate": 2.74374460742019e-06,
2113
+ "loss": 2.7467,
2114
+ "step": 174000
2115
+ },
2116
+ {
2117
+ "epoch": 2.6,
2118
+ "learning_rate": 2.6941576666369145e-06,
2119
+ "loss": 2.7633,
2120
+ "step": 174500
2121
+ },
2122
+ {
2123
+ "epoch": 2.6,
2124
+ "learning_rate": 2.6445707258536394e-06,
2125
+ "loss": 2.7681,
2126
+ "step": 175000
2127
+ },
2128
+ {
2129
+ "epoch": 2.61,
2130
+ "learning_rate": 2.594983785070364e-06,
2131
+ "loss": 2.7552,
2132
+ "step": 175500
2133
+ },
2134
+ {
2135
+ "epoch": 2.62,
2136
+ "learning_rate": 2.5453968442870885e-06,
2137
+ "loss": 2.7539,
2138
+ "step": 176000
2139
+ },
2140
+ {
2141
+ "epoch": 2.63,
2142
+ "learning_rate": 2.4958099035038134e-06,
2143
+ "loss": 2.7393,
2144
+ "step": 176500
2145
  }
2146
  ],
2147
  "max_steps": 201666,
2148
  "num_train_epochs": 3,
2149
+ "total_flos": 2.0788079286996173e+17,
2150
  "trial_name": null,
2151
  "trial_params": null
2152
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a5ec2ac5d923b5dd8a99ca581137ee6c85b4ea12bee1568d23a8455d2a58084
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2991727b803e8a0b02542f03f6557f0258a9e36d172bbf826844685e5c5185
3
  size 1200739717
runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7dd64fd5f5ee57511fff720cbb56340f4a2adf91133fae41a0df73cab017476
3
- size 57631
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e4f0ed5da7d5706ba5011c8ef271d1d10c08c2a0dcb249dc605188bb19cec7
3
+ size 61151