Training in progress, step 6080, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26556f1abb53ee822dd03ecead2e694e90d90f9f7c06255c3fb3bb5bd95b1e95
+oid sha256:0fa290a324b0413b280d2bace84c9e16ff480cfdf57669d0e4aa091cc96a7f3a
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5267791793a613d797a09d60c3e5961f54bab0e1981820004fbccdcc8050fd4a
+oid sha256:155d752646efe8e0f6b33728b9a2153eb61f59385cfa4bc37a58d1e634a84306
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c1b58129752e66a4a302f63e7677b4460963afc004711e8b13996046bcd2c8
+oid sha256:f1814d7b39176db5919fcc37c67d779f76326615526c5fa198e939a90b9adff4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45e18651ea77eb43c3817495dab8ccf485a98bc6d621a0b971d270fe188b5ec
+oid sha256:541ffa1c9c0ef80e1cac33b6e46c86e1b24666070b4e0e70f8ae6ca13ce53e48
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4816,
+  "epoch": 0.4864,
   "eval_steps": 500,
-  "global_step": 6020,
+  "global_step": 6080,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2114,6 +2114,27 @@
       "learning_rate": 2.4583801313868417e-05,
       "loss": 3.4601,
       "step": 6020
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 36.80402374267578,
+      "learning_rate": 2.4546378803728922e-05,
+      "loss": 3.5053,
+      "step": 6040
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 25.655963897705078,
+      "learning_rate": 2.450885615659305e-05,
+      "loss": 3.4791,
+      "step": 6060
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 47.66796112060547,
+      "learning_rate": 2.447123376605561e-05,
+      "loss": 3.4535,
+      "step": 6080
     }
   ],
   "logging_steps": 20,
@@ -2121,7 +2142,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.4256891905015808e+16,
+  "total_flos": 1.4386015976914944e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null