End of training

README.md

@@ -14,11 +14,11 @@ 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: 4.4277
-- eval_runtime: 0.0266
-- eval_samples_per_second: 75.081
-- eval_steps_per_second: 37.541
-- epoch: 5.0
-- step: 5
+- eval_runtime: 0.0432
+- eval_samples_per_second: 46.32
+- eval_steps_per_second: 23.16
+- epoch: 1.0
+- step: 1
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10193bcc86113343252341e92207017fb141a3032e342ffbfeff64334bf87001
+oid sha256:cfc3b0a6ffd5b8f17378f6012aefc278f489bb7233780f269eb1cabd977a5237
 size 435820636

runs/Jan05_08-11-12_414819e23027/events.out.tfevents.1704442276.414819e23027.9579.17

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb6071f5ff5a33a5778d83e18689aa09ab5bf07513de3cecadbbd8917d45380
-size 9527
+oid sha256:e6b3f501d565d135853e2625fc9408912a52487272d32a13509dbdb4f589084e
+size 9947

runs/Jan05_08-13-40_414819e23027/events.out.tfevents.1704442424.414819e23027.9579.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfcb1fd4472ae9300d3e268820e10cbe3fbdc809768f742fc89f460f8c31d72
+size 7847

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 1.0,
   "eval_steps": 1,
-  "global_step": 5,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,79 +11,23 @@
     {
       "epoch": 1.0,
       "learning_rate": 4.9e-05,
-      "loss": 2.9799,
+      "loss": 1.7032,
       "step": 1
     },
     {
       "epoch": 1.0,
-      "eval_loss": 4.379878520965576,
-      "eval_runtime": 0.0344,
-      "eval_samples_per_second": 58.156,
-      "eval_steps_per_second": 29.078,
+      "eval_loss": 4.427746772766113,
+      "eval_runtime": 0.0432,
+      "eval_samples_per_second": 46.32,
+      "eval_steps_per_second": 23.16,
       "step": 1
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 4.8e-05,
-      "loss": 2.8715,
-      "step": 2
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 4.377772331237793,
-      "eval_runtime": 0.0396,
-      "eval_samples_per_second": 50.454,
-      "eval_steps_per_second": 25.227,
-      "step": 2
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 4.7e-05,
-      "loss": 2.7802,
-      "step": 3
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 4.3962507247924805,
-      "eval_runtime": 0.0322,
-      "eval_samples_per_second": 62.025,
-      "eval_steps_per_second": 31.012,
-      "step": 3
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 4.600000000000001e-05,
-      "loss": 2.7155,
-      "step": 4
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 4.412981033325195,
-      "eval_runtime": 0.0322,
-      "eval_samples_per_second": 62.162,
-      "eval_steps_per_second": 31.081,
-      "step": 4
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 4.5e-05,
-      "loss": 2.5694,
-      "step": 5
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 4.427673816680908,
-      "eval_runtime": 0.0266,
-      "eval_samples_per_second": 75.081,
-      "eval_steps_per_second": 37.541,
-      "step": 5
     }
   ],
   "logging_steps": 1,
   "max_steps": 50,
   "num_train_epochs": 50,
   "save_steps": 20,
-  "total_flos": 2880246762000.0,
+  "total_flos": 576049352400.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee86837266bbc5e6172c9e09bcb500cf131b1fcc7f02b545c8245aad1f23abde
+oid sha256:b554a0f7ab4b7d3244fac3afa1785f5d08bd92fbd8650dc39823806b8d9c0513
 size 4600