Training in progress, step 12500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0270219bbf3b9d435456104809f3c23a41c4cd1fe51a03b95efb36b90021a044
+oid sha256:fcf16c77fc4c696d5ecec66bb94ab1a72596ecc42da185a1509a0a37aa93d820
 size 1115513717

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b3509860f8b9090ce37e24daf382d92def3c20605929d105fc7709bfdf4fa92
+oid sha256:001276adc811be2b4e3383d1bfd82644ee01b63c562240704981e80abf57ea78
 size 557969145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd78237a8bff2399c24e5136a001794a3e1c14fbfcbde9fa5704a4fcf3d3828
+oid sha256:3ea4cb9a85921bdde5a8523300b183bff3f70a1aeb0368e6a4c669b696d1922c
 size 15523

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6cc4eff0bedca1e1ffd7c8824dc4da7fe034832dbf96d075af2be5a88f8f30
+oid sha256:af29429f2a56160c0a3cb3b03c7b28cc9e5f472234bebefa86da284747a0d6d1
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1485012059262663,
-  "global_step": 10000,
+  "epoch": 1.4356265074078327,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -606,11 +606,161 @@
       "learning_rate": 1.8098002934983733e-05,
       "loss": 0.5978,
       "step": 10000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.7778982964333567e-05,
+      "loss": 0.6034,
+      "step": 10100
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.7459962993683405e-05,
+      "loss": 0.6037,
+      "step": 10200
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.7140943023033243e-05,
+      "loss": 0.6251,
+      "step": 10300
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.6821923052383077e-05,
+      "loss": 0.581,
+      "step": 10400
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.650290308173292e-05,
+      "loss": 0.5919,
+      "step": 10500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.6183883111082753e-05,
+      "loss": 0.6073,
+      "step": 10600
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.5864863140432594e-05,
+      "loss": 0.6273,
+      "step": 10700
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.554584316978243e-05,
+      "loss": 0.6198,
+      "step": 10800
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.5226823199132268e-05,
+      "loss": 0.5993,
+      "step": 10900
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.4907803228482104e-05,
+      "loss": 0.5519,
+      "step": 11000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.4588783257831942e-05,
+      "loss": 0.6152,
+      "step": 11100
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.4269763287181778e-05,
+      "loss": 0.6251,
+      "step": 11200
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.3950743316531614e-05,
+      "loss": 0.6747,
+      "step": 11300
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3631723345881454e-05,
+      "loss": 0.6253,
+      "step": 11400
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.331270337523129e-05,
+      "loss": 0.6009,
+      "step": 11500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2993683404581127e-05,
+      "loss": 0.6019,
+      "step": 11600
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2674663433930964e-05,
+      "loss": 0.6286,
+      "step": 11700
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2355643463280801e-05,
+      "loss": 0.5796,
+      "step": 11800
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2036623492630639e-05,
+      "loss": 0.6077,
+      "step": 11900
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1717603521980477e-05,
+      "loss": 0.6186,
+      "step": 12000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1398583551330313e-05,
+      "loss": 0.6632,
+      "step": 12100
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.107956358068015e-05,
+      "loss": 0.5796,
+      "step": 12200
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0760543610029989e-05,
+      "loss": 0.5951,
+      "step": 12300
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.0441523639379826e-05,
+      "loss": 0.5743,
+      "step": 12400
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.0122503668729662e-05,
+      "loss": 0.6705,
+      "step": 12500
     }
   ],
   "max_steps": 15673,
   "num_train_epochs": 2,
-  "total_flos": 3.954111338032128e+16,
+  "total_flos": 4.939903709604864e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b3509860f8b9090ce37e24daf382d92def3c20605929d105fc7709bfdf4fa92
+oid sha256:001276adc811be2b4e3383d1bfd82644ee01b63c562240704981e80abf57ea78
 size 557969145

runs/Jan26_03-13-45_b3489f7155a5/events.out.tfevents.1674703022.b3489f7155a5.24.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e582d90f7535fdd56e7dc87ed69608bed0f439782a1664c33152ca1b8568bf2f
-size 20535
+oid sha256:f77dd77e2e1de62f98d722747a220a5ac16ebff7589985b9d63fb7e5c44b6c35
+size 24460