Training in progress, step 110000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "DeepESP/gpt2-spanish",
+  "_name_or_path": "MarkelFe/PoliticalSpeech2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

last-checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "DeepESP/gpt2-spanish",
+  "_name_or_path": "MarkelFe/PoliticalSpeech2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a1421f8e6cb5bb67425311aef9dda9661c917aab4a357a23ec44b2e3daab85
+oid sha256:4a9bc8c12cb2cf6ed3ccb5b585450d138e62bee12142711a3446cb1a0dc2a7c1
 size 995605445

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f16473c3f1ed9f0581444acbd15664c381713c51843177e152cb72b1bd63766
+oid sha256:64b7857fda6aab7245b90375ddb99a6ea560cd4b8c3a5c8e8a357ebcea3a71db
 size 510398013

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:412df950fe881812d4df452ea4ec2fcd612c8449348c26dda4f3e5ddd7d9a49a
+oid sha256:39a74b88b3614b3e58ed0796513c6c2b83a26d8f63a05b20d3ddb63f51d8cfd5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61191d318bf68e1245e4fc98bbc55f1b8337c3d4b3f28a8adc2b1ca718b159b
+oid sha256:98d37f2648c88f2e98f12ff7b39e7b8b0f53d4838c5848eaeff572e95b5d5ca3
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.367648451557913,
-  "global_step": 100000,
+  "epoch": 2.604413296713704,
+  "global_step": 110000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1292,11 +1292,139 @@
       "eval_samples_per_second": 166.106,
       "eval_steps_per_second": 20.768,
       "step": 100000
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.644353947659185e-05,
+      "loss": 2.766,
+      "step": 100500
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.638040218455031e-05,
+      "loss": 2.7858,
+      "step": 101000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.631726489250876e-05,
+      "loss": 2.7735,
+      "step": 101500
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.6254127600467217e-05,
+      "loss": 2.7908,
+      "step": 102000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.6190990308425672e-05,
+      "loss": 2.814,
+      "step": 102500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.6127853016384127e-05,
+      "loss": 2.7823,
+      "step": 103000
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 2.6064715724342585e-05,
+      "loss": 2.7855,
+      "step": 103500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.600157843230104e-05,
+      "loss": 2.7984,
+      "step": 104000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 2.5938441140259496e-05,
+      "loss": 2.8117,
+      "step": 104500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 2.587530384821795e-05,
+      "loss": 2.8052,
+      "step": 105000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.581216655617641e-05,
+      "loss": 2.8137,
+      "step": 105500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 2.5749029264134864e-05,
+      "loss": 2.8106,
+      "step": 106000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 2.568589197209332e-05,
+      "loss": 2.796,
+      "step": 106500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.5622754680051775e-05,
+      "loss": 2.8181,
+      "step": 107000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 2.5559617388010233e-05,
+      "loss": 2.806,
+      "step": 107500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 2.5496480095968688e-05,
+      "loss": 2.8292,
+      "step": 108000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.5433342803927143e-05,
+      "loss": 2.8104,
+      "step": 108500
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.53702055118856e-05,
+      "loss": 2.8292,
+      "step": 109000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.530706821984405e-05,
+      "loss": 2.8115,
+      "step": 109500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 2.524393092780251e-05,
+      "loss": 2.8272,
+      "step": 110000
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 3.1270127296447754,
+      "eval_runtime": 113.6604,
+      "eval_samples_per_second": 165.159,
+      "eval_steps_per_second": 20.649,
+      "step": 110000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 2.120856134976e+16,
+  "total_flos": 2.332982396736e+16,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13bd02ff5c40117ddbf942838af2297189fae003bd9b651003f2826488ee929
+oid sha256:2ae549f0bd35c85b2cbb303f165785a4c8cb5d499cfc8e300500dad5f12d79c4
 size 4987

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f16473c3f1ed9f0581444acbd15664c381713c51843177e152cb72b1bd63766
+oid sha256:64b7857fda6aab7245b90375ddb99a6ea560cd4b8c3a5c8e8a357ebcea3a71db
 size 510398013

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13bd02ff5c40117ddbf942838af2297189fae003bd9b651003f2826488ee929
+oid sha256:2ae549f0bd35c85b2cbb303f165785a4c8cb5d499cfc8e300500dad5f12d79c4
 size 4987