Training in progress, step 96, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:611732e8b60b82f65ca3fb621af02d76e06289cda1042b9cb51448095f7f99f2
+oid sha256:10dd6e59839697983ac7357e410711a9437ba43312590efd839cd9b3c1eaf5ee
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b78fd360fd0837a0e24e78ff53bcb54596b905619d3f1795815dbe338f7fdc0
+oid sha256:87674fb31f651703f67324edeb4965dd0bab54531a95f1888f2f0b1f8a781f10
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea3603c9a5ac93aadff8538e8c1f7b7097253fb14e88f0b33e0bdddfa5087f6
+oid sha256:20741c0db4af8011c95f93fd02a96b812116cb014b8f60028a24e84ef0e0f0a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bd97bc98e39f7007b5f2750d097c7395ce4bde9cd90085b1ec2b6c643faaf8
+oid sha256:80ffdba0827548f3b413b86d873a6fdae4989ec2c782588463bc4ec0efdb484e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.75,
+  "epoch": 1.0,
   "eval_steps": 24,
-  "global_step": 72,
+  "global_step": 96,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,70 @@
       "eval_samples_per_second": 48.555,
       "eval_steps_per_second": 6.294,
       "step": 72
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.3321720063686371,
+      "learning_rate": 4.355339409154788e-05,
+      "loss": 1.4901,
+      "step": 75
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 0.349568635225296,
+      "learning_rate": 4.297477038394368e-05,
+      "loss": 1.5304,
+      "step": 78
+    },
+    {
+      "epoch": 0.84375,
+      "grad_norm": 0.38185468316078186,
+      "learning_rate": 4.237548933539718e-05,
+      "loss": 1.502,
+      "step": 81
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.37284818291664124,
+      "learning_rate": 4.1756239664188273e-05,
+      "loss": 1.4548,
+      "step": 84
+    },
+    {
+      "epoch": 0.90625,
+      "grad_norm": 0.3401886522769928,
+      "learning_rate": 4.1117733037354314e-05,
+      "loss": 1.49,
+      "step": 87
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.31730660796165466,
+      "learning_rate": 4.0460703252813326e-05,
+      "loss": 1.485,
+      "step": 90
+    },
+    {
+      "epoch": 0.96875,
+      "grad_norm": 0.34687182307243347,
+      "learning_rate": 3.978590539605338e-05,
+      "loss": 1.5021,
+      "step": 93
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4444548487663269,
+      "learning_rate": 3.9094114972357524e-05,
+      "loss": 1.4711,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.452917218208313,
+      "eval_runtime": 3.3544,
+      "eval_samples_per_second": 48.294,
+      "eval_steps_per_second": 6.26,
+      "step": 96
     }
   ],
   "logging_steps": 3,
@@ -226,7 +290,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6211923678789632e+16,
+  "total_flos": 2.1558125484048384e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null