Upload folder using huggingface_hub (#4)

- Upload folder using huggingface_hub (130c3dcb3e4a25cc6bc802c0e664010d3fc7fc13)

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "total_flos": 2.3867532801294336e+16,
-    "train_loss": 0.23429088592529296,
-    "train_runtime": 606.0988,
-    "train_samples_per_second": 0.508,
-    "train_steps_per_second": 0.033
+    "total_flos": 2.944695605354496e+16,
+    "train_loss": 0.2903190416594346,
+    "train_runtime": 752.2275,
+    "train_samples_per_second": 0.505,
+    "train_steps_per_second": 0.032
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15269333bc7d6f6f273da0d22ccd4642cc1fbc0c74992c380b89974006f429cd
+oid sha256:efc60ed5e083d25f88629d8f1fe0745ab94fbf58e28492cc591b6f22d62767d6
 size 343223968

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "total_flos": 2.3867532801294336e+16,
-    "train_loss": 0.23429088592529296,
-    "train_runtime": 606.0988,
-    "train_samples_per_second": 0.508,
-    "train_steps_per_second": 0.033
+    "total_flos": 2.944695605354496e+16,
+    "train_loss": 0.2903190416594346,
+    "train_runtime": 752.2275,
+    "train_samples_per_second": 0.505,
+    "train_steps_per_second": 0.032
 }

trainer_state.json

@@ -3,41 +3,41 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 40,
-  "global_step": 20,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 2.0,
-      "grad_norm": 0.5412699580192566,
-      "learning_rate": 0.0001,
-      "loss": 0.344,
+      "epoch": 1.67,
+      "grad_norm": 1.1704062223434448,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 0.4643,
       "step": 10
     },
     {
-      "epoch": 4.0,
-      "grad_norm": 0.285557359457016,
-      "learning_rate": 0.0,
-      "loss": 0.1246,
+      "epoch": 3.33,
+      "grad_norm": 0.49445489048957825,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.1939,
       "step": 20
     },
     {
       "epoch": 4.0,
-      "step": 20,
-      "total_flos": 2.3867532801294336e+16,
-      "train_loss": 0.23429088592529296,
-      "train_runtime": 606.0988,
-      "train_samples_per_second": 0.508,
-      "train_steps_per_second": 0.033
+      "step": 24,
+      "total_flos": 2.944695605354496e+16,
+      "train_loss": 0.2903190416594346,
+      "train_runtime": 752.2275,
+      "train_samples_per_second": 0.505,
+      "train_steps_per_second": 0.032
     }
   ],
   "logging_steps": 10,
-  "max_steps": 20,
+  "max_steps": 24,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 40,
-  "total_flos": 2.3867532801294336e+16,
+  "total_flos": 2.944695605354496e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d75a73478186eb85b24b38e631dac421017fb41bb95161a7d4d42aef1f2ab8f3
+oid sha256:5b643b1cc4fdec24b23924b3d9c8bf8452e1cdd15e0a50c9c9d4f621c74781bb
 size 4920