Training in progress, step 6160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa290a324b0413b280d2bace84c9e16ff480cfdf57669d0e4aa091cc96a7f3a
+oid sha256:3e5f6360dfa9c2a789402315eb51b17d5c5437a5e36f3a7f4a8ff1180c978bd7
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155d752646efe8e0f6b33728b9a2153eb61f59385cfa4bc37a58d1e634a84306
+oid sha256:ef67c02a39ed9ea9db9f9f9072b9280130156e0f2c168f6d3433e11a691906a0
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1814d7b39176db5919fcc37c67d779f76326615526c5fa198e939a90b9adff4
+oid sha256:059a6e0450ff9489b2174c9501bf25eb13b58d453dbd5dc4fed1c213de807539
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541ffa1c9c0ef80e1cac33b6e46c86e1b24666070b4e0e70f8ae6ca13ce53e48
+oid sha256:1291563f0ece66a71bc509a68887ccf6e08065ec53a4ab16c369d685623ef0fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4864,
+  "epoch": 0.4928,
   "eval_steps": 500,
-  "global_step": 6080,
+  "global_step": 6160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2135,6 +2135,34 @@
       "learning_rate": 2.447123376605561e-05,
       "loss": 3.4535,
       "step": 6080
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 39.040924072265625,
+      "learning_rate": 2.4433512026757668e-05,
+      "loss": 3.5125,
+      "step": 6100
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 27.91790008544922,
+      "learning_rate": 2.439569133438243e-05,
+      "loss": 3.5131,
+      "step": 6120
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 42.502357482910156,
+      "learning_rate": 2.435777208565106e-05,
+      "loss": 3.5424,
+      "step": 6140
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 26.83557891845703,
+      "learning_rate": 2.431975467831853e-05,
+      "loss": 3.4445,
+      "step": 6160
     }
   ],
   "logging_steps": 20,
@@ -2142,7 +2170,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.4386015976914944e+16,
+  "total_flos": 1.4563889634902016e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null