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:ffe100ff12f84949362cc9090e3a174b81ae45332a05f58de933ebc14d72408f
+oid sha256:c1cd6fa7488f5ebec771a8b0b2a5e082550394febfd304442aea6a9b9bd40634
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b8e48c6ab78a091b59c8338451f85cca811219797f48fabd42693ca3228689
+oid sha256:81bdb4e163aac6881fa8985dbc72e21986d407a42f675b6b78572d02b559d8db
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4ea1dbe1dfcdacf872ade67628a94a19f9881d46e8f54110ae221a382e82125
+oid sha256:baacc8adb5b1f537298b9ceb42d97a30d074c4b147330d0a8447401d9393d584
 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": 24.915,
       "eval_steps_per_second": 12.458,
       "step": 3
+    },
+    {
+      "epoch": 0.0003447310020899317,
+      "grad_norm": 1.6838661432266235,
+      "learning_rate": 8e-05,
+      "loss": 1.7573,
+      "step": 4
+    },
+    {
+      "epoch": 0.0004309137526124146,
+      "grad_norm": 1.3160624504089355,
+      "learning_rate": 0.0001,
+      "loss": 1.49,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005170965031348976,
+      "grad_norm": 1.4394317865371704,
+      "learning_rate": 0.00012,
+      "loss": 1.7809,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005170965031348976,
+      "eval_loss": NaN,
+      "eval_runtime": 196.1687,
+      "eval_samples_per_second": 24.907,
+      "eval_steps_per_second": 12.454,
+      "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