End of training

README.md

@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 4.4389
-- eval_runtime: 0.03
-- eval_samples_per_second: 66.75
-- eval_steps_per_second: 33.375
-- epoch: 3.0
-- step: 3
+- eval_loss: 4.4745
+- eval_runtime: 0.0352
+- eval_samples_per_second: 56.755
+- eval_steps_per_second: 28.378
+- epoch: 5.0
+- step: 5
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a8c976af2ce497cc177ad5637552212b541c7429801f42b80b6c2151a37ca8
+oid sha256:212a1c7f39f2726ed5816603afecb3c1759c9ce41e6f17b37163aa50ffcfc75e
 size 435820636

runs/Jan05_08-15-17_414819e23027/events.out.tfevents.1704442521.414819e23027.9579.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:249bbbd4afebe7c23b2510ca5d0f1ecc7cb669509e30e3bcbb913330da954f6e
-size 8686
+oid sha256:096d1cc74d658c221b1bafbdb5eba614bc035db22f5fb6b974fbdd0ff091ea2e
+size 9106

runs/Jan05_08-17-01_414819e23027/events.out.tfevents.1704442625.414819e23027.9579.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d599d3f5d41b87d3735fc7fbf441d9b36f4ada6f6d4ef337b44970b6fc42f707
+size 7846

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 1,
-  "global_step": 3,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,13 +49,41 @@
       "eval_samples_per_second": 66.75,
       "eval_steps_per_second": 33.375,
       "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.757,
+      "step": 4
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.466496467590332,
+      "eval_runtime": 0.0321,
+      "eval_samples_per_second": 62.331,
+      "eval_steps_per_second": 31.165,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.9e-05,
+      "loss": 1.5364,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.474534034729004,
+      "eval_runtime": 0.0352,
+      "eval_samples_per_second": 56.755,
+      "eval_steps_per_second": 28.378,
+      "step": 5
     }
   ],
   "logging_steps": 1,
   "max_steps": 50,
   "num_train_epochs": 50,
   "save_steps": 20,
-  "total_flos": 1728148057200.0,
+  "total_flos": 2880246762000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b966ffecbed91c5a0f2c413b6fea27a6d5dcd1ad5d43f2d92aea5836886021b2
+oid sha256:6fd8735572c360aff55483202835ae93d2da4df07d250cdf37afb9452e9a7fdf
 size 4600