Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df63218267c60796269be9c086398529aaac3db7140acae0617cb0008913f250
+oid sha256:b26a569cc578738d3abf1bf2b5f46773b47763d9b531b16283f08583a646b111
 size 268290900

run-4/checkpoint-1000/trainer_state.json

@@ -10,57 +10,57 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5770967741935484,
-      "eval_loss": 0.21370309591293335,
-      "eval_runtime": 14.0528,
-      "eval_samples_per_second": 220.597,
-      "eval_steps_per_second": 27.61,
+      "eval_accuracy": 0.5838709677419355,
+      "eval_loss": 0.21017009019851685,
+      "eval_runtime": 14.176,
+      "eval_samples_per_second": 218.679,
+      "eval_steps_per_second": 27.37,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.547938346862793,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.3338,
+      "grad_norm": 0.5476248264312744,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3313,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8070967741935484,
-      "eval_loss": 0.10994400829076767,
-      "eval_runtime": 14.8624,
-      "eval_samples_per_second": 208.58,
-      "eval_steps_per_second": 26.106,
+      "eval_accuracy": 0.8132258064516129,
+      "eval_loss": 0.1052323654294014,
+      "eval_runtime": 15.1302,
+      "eval_samples_per_second": 204.889,
+      "eval_steps_per_second": 25.644,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8664516129032258,
-      "eval_loss": 0.07803630828857422,
-      "eval_runtime": 14.0685,
-      "eval_samples_per_second": 220.351,
-      "eval_steps_per_second": 27.579,
+      "eval_accuracy": 0.8735483870967742,
+      "eval_loss": 0.0720921978354454,
+      "eval_runtime": 15.183,
+      "eval_samples_per_second": 204.176,
+      "eval_steps_per_second": 25.555,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.510848343372345,
-      "learning_rate": 7.421383647798742e-06,
-      "loss": 0.1268,
+      "grad_norm": 0.5215755701065063,
+      "learning_rate": 9.517819706498952e-06,
+      "loss": 0.1213,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1590,
+  "max_steps": 1908,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 6,
   "save_steps": 500,
   "total_flos": 260941334653608.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.7585287445252074,
-    "num_train_epochs": 5,
+    "alpha": 0.26249257567606554,
+    "num_train_epochs": 6,
     "temperature": 9
   }
 }

run-4/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c58a50c849b52be08129cef2729104b91f5ebaf46457436ac0e5ddb0274590
+oid sha256:b26a569cc578738d3abf1bf2b5f46773b47763d9b531b16283f08583a646b111
 size 268290900

run-4/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28a1e8094eb6ab9663cd2fb830933ca60972e0ea885d2d509150b1efcbf6e84
+oid sha256:9de0cd572250a185f7a507f74cf7a8ced3aced327cf408cb338756a912031ff2
 size 536643898

run-4/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f75fa3851d3548c8bbed0ee7c49e6a23f30f028b074a4398b38c7ecbd0f8e9
+oid sha256:40a61c60e2a1f354f14fb973803108ea16a9c8c66946147c407c26a5211c4f3d
 size 1064

run-4/checkpoint-500/trainer_state.json

@@ -10,32 +10,32 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5770967741935484,
-      "eval_loss": 0.21370309591293335,
-      "eval_runtime": 14.0528,
-      "eval_samples_per_second": 220.597,
-      "eval_steps_per_second": 27.61,
+      "eval_accuracy": 0.5838709677419355,
+      "eval_loss": 0.21017009019851685,
+      "eval_runtime": 14.176,
+      "eval_samples_per_second": 218.679,
+      "eval_steps_per_second": 27.37,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.547938346862793,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.3338,
+      "grad_norm": 0.5476248264312744,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3313,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1590,
+  "max_steps": 1908,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 6,
   "save_steps": 500,
   "total_flos": 130072209152340.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.7585287445252074,
-    "num_train_epochs": 5,
+    "alpha": 0.26249257567606554,
+    "num_train_epochs": 6,
     "temperature": 9
   }
 }

run-4/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ebf3e57ce79f923f7e5aafb794af408f66b4986abca9ae9dc5272fd223fd4c7
+oid sha256:2268c870be35630cfe13ebf1fbf99fa08a02eaaf00eb138b06a85b1f51fe6863
 size 5048

runs/May19_07-23-12_MainPC/events.out.tfevents.1716074034.MainPC.190288.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4753a8940564f513132ec769154ff223676aded564c0e557983a82ec9d1d0eda
-size 14453
+oid sha256:2706c5a7a0af766114b9b71fee4325a94d0cc033fa30363fa2f711476e0914a9
+size 15130

runs/May19_07-23-12_MainPC/events.out.tfevents.1716074331.MainPC.190288.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3de3126e6a301ceff96696a2b8f1b4aa10034c9c0f98ac6762b1f55ebb255a0
+size 13062

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85cc43ec40a41c2d6ebea072a229c801250429a053cee51af906adb3742fabd9
+oid sha256:2268c870be35630cfe13ebf1fbf99fa08a02eaaf00eb138b06a85b1f51fe6863
 size 5048