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:ec6689c4614d98b9776cfb06f3965f3fed48765e54b32abc3b26b54d2551b30b
+oid sha256:36d785dc9f57dbb0fd5b895bbd1011197fd62f45ebb01ddde0b5ecf09b383476
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db68d02f3273de0f48fd782ea904443a51c4d736d816de0ff68f97ed5a1a1619
+oid sha256:a7faa0969227a7d6e13277f269736a424418b7fae9686bfaa187d7b65cc9022e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
+oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
 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": 0.013714285714285714,
+  "epoch": 0.027428571428571427,
   "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": 17.919,
       "eval_steps_per_second": 9.056,
       "step": 3
+    },
+    {
+      "epoch": 0.018285714285714287,
+      "grad_norm": 0.7289955615997314,
+      "learning_rate": 8e-05,
+      "loss": 2.9317,
+      "step": 4
+    },
+    {
+      "epoch": 0.022857142857142857,
+      "grad_norm": 0.8006905317306519,
+      "learning_rate": 0.0001,
+      "loss": 2.8297,
+      "step": 5
+    },
+    {
+      "epoch": 0.027428571428571427,
+      "grad_norm": 0.9357383847236633,
+      "learning_rate": 0.00012,
+      "loss": 3.3155,
+      "step": 6
+    },
+    {
+      "epoch": 0.027428571428571427,
+      "eval_loss": 2.8182923793792725,
+      "eval_runtime": 5.1986,
+      "eval_samples_per_second": 17.89,
+      "eval_steps_per_second": 9.041,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 2219477097775104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null