Training in progress, step 650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b35aacbfdc92cae95f4722e8ccfc67a4f68647ffa65ea431590ce58096dec808
+oid sha256:77bec1f4ac425531a05582ea8046293677e9aef7e25a09da01544099efb93f8d
 size 1912664024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49e207697dc3ec720bb6feb8f8eae1a74a911ee9fb54850c4480006eaa332e55
+oid sha256:c62765d738accf85fc7c3f65162136ac7c75de679fcbaa389480de246257616a
 size 958697812

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d248dd4a61bc85f685999c311d599535fb345e57d98e4ccefd0735e695f9bd
+oid sha256:f0ab450b6ed3afea5706163f591f78b56c95466e0ef81af351a47a99261b91e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc36f0303920d64d6d5947100d6f9f34e124ede65e136b78d6101e85e913cf9
+oid sha256:b1b4f26951b84f5727f8b34d9245ef840230c09420a237b4b37e336f28fe1f3c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03681207436039021,
+  "epoch": 0.039879747223756055,
   "eval_steps": 20,
-  "global_step": 600,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,6 +457,36 @@
       "eval_samples_per_second": 4.229,
       "eval_steps_per_second": 0.55,
       "step": 600
+    },
+    {
+      "epoch": 0.03803914350573655,
+      "grad_norm": 0.1577584445476532,
+      "learning_rate": 0.00019245120903400024,
+      "loss": 1.5497,
+      "step": 620
+    },
+    {
+      "epoch": 0.03803914350573655,
+      "eval_loss": 1.4203659296035767,
+      "eval_runtime": 23.8622,
+      "eval_samples_per_second": 4.191,
+      "eval_steps_per_second": 0.545,
+      "step": 620
+    },
+    {
+      "epoch": 0.03926621265108289,
+      "grad_norm": 0.12410438805818558,
+      "learning_rate": 0.00019220571989689457,
+      "loss": 1.503,
+      "step": 640
+    },
+    {
+      "epoch": 0.03926621265108289,
+      "eval_loss": 1.4154139757156372,
+      "eval_runtime": 23.4706,
+      "eval_samples_per_second": 4.261,
+      "eval_steps_per_second": 0.554,
+      "step": 640
     }
   ],
   "logging_steps": 20,
@@ -464,7 +494,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 50,
-  "total_flos": 4.3772694621696e+16,
+  "total_flos": 4.730105544192e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null