Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c8c75acc4c36fe77ecc5d815d8dd25bb0d859defca44c9565b9e35a42c4a98
+oid sha256:cf3bfa55097dd5bb5e93a4a31c9922f5a7f22f0ab122afd5251049053c0a7fb3
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da39bfee23312cad7006db19413c2af6eb37fc944bc37ee57e0e90abbfd6a0a
+oid sha256:995fa7975b98ba6736f922c9006d080bf1210cea36826ec7e34640f1a8a2a170
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4f1867aa16bfa15890834518ba57df0aa25651cc5a9f868d2c781295bd438e
+oid sha256:568ee55b83fd3bf20664b59f33f857dcb4b212e91aa3990c870da955df7bec07
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002585482515674488,
+  "epoch": 0.0005170965031348976,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 24.797,
       "eval_steps_per_second": 12.398,
       "step": 3
+    },
+    {
+      "epoch": 0.0003447310020899317,
+      "grad_norm": 1.4771511554718018,
+      "learning_rate": 8e-05,
+      "loss": 1.7685,
+      "step": 4
+    },
+    {
+      "epoch": 0.0004309137526124146,
+      "grad_norm": 1.1435108184814453,
+      "learning_rate": 0.0001,
+      "loss": 1.4952,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005170965031348976,
+      "grad_norm": 1.2580000162124634,
+      "learning_rate": 0.00012,
+      "loss": 1.7866,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005170965031348976,
+      "eval_loss": NaN,
+      "eval_runtime": 197.1878,
+      "eval_samples_per_second": 24.778,
+      "eval_steps_per_second": 12.389,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 348520682618880.0,
+  "total_flos": 676540148613120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null