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:c77eb5c0827e84036813331915277ae0c0f49495d93704dea7948e23282322e9
+oid sha256:980512ee695cc6be6c28f785540821e6ff22107bbb2abeebf3c7ea3710533e95
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca09163e23e3d23721bc719c4cfff767cc6ca8d67474d6b3f2129ab82e7a3f30
+oid sha256:76cd143f39ecc6ed2287102a67055e5246aef4bca1621fdc2cac79f08417abf3
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c577fa0d5440076aa59215302dbde6f36234cd1bbefdcf145b0d95592f175e6c
+oid sha256:3834acef3f7d0460f517eef54fb9e752ced2048603b5633c411f56f883afb7c5
 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": 0.00037809565820152497,
+  "epoch": 0.0007561913164030499,
   "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": 51.027,
       "eval_steps_per_second": 25.521,
       "step": 3
+    },
+    {
+      "epoch": 0.0005041275442687,
+      "grad_norm": 0.8987447023391724,
+      "learning_rate": 8e-05,
+      "loss": 1.0111,
+      "step": 4
+    },
+    {
+      "epoch": 0.0006301594303358749,
+      "grad_norm": 0.7501655220985413,
+      "learning_rate": 0.0001,
+      "loss": 1.0644,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007561913164030499,
+      "grad_norm": 0.6338196992874146,
+      "learning_rate": 0.00012,
+      "loss": 0.9401,
+      "step": 6
+    },
+    {
+      "epoch": 0.0007561913164030499,
+      "eval_loss": 1.0883917808532715,
+      "eval_runtime": 66.1456,
+      "eval_samples_per_second": 50.51,
+      "eval_steps_per_second": 25.262,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 40067173711872.0,
+  "total_flos": 84586255613952.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null