Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12178febf42a052b527fc2fd9cb8e5f58e7a72936805f736e44e8ef06aa18d0e
+oid sha256:31a91b74719ad68a1b5c21e5c74c443202d5ca7acf928158e09bea951890f60e
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f1c2e743001c08bbfc8f15e49ba897fcee5decd79b3328f9a5bce08ab5c5d9
+oid sha256:7a92b80f1046dd51ec05df546fd4ae4eb94c0f01945d72df0ac15b152bdc012c
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 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": 0.005215123859191656,
+  "epoch": 0.010430247718383311,
   "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": 120.478,
       "eval_steps_per_second": 60.487,
       "step": 3
+    },
+    {
+      "epoch": 0.006953498478922208,
+      "grad_norm": 0.05050083249807358,
+      "learning_rate": 8e-05,
+      "loss": 10.376,
+      "step": 4
+    },
+    {
+      "epoch": 0.008691873098652759,
+      "grad_norm": 0.042805321514606476,
+      "learning_rate": 0.0001,
+      "loss": 10.3728,
+      "step": 5
+    },
+    {
+      "epoch": 0.010430247718383311,
+      "grad_norm": 0.041813645511865616,
+      "learning_rate": 0.00012,
+      "loss": 10.3757,
+      "step": 6
+    },
+    {
+      "epoch": 0.010430247718383311,
+      "eval_loss": 10.373467445373535,
+      "eval_runtime": 2.0449,
+      "eval_samples_per_second": 118.833,
+      "eval_steps_per_second": 59.661,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77585448960.0,
+  "total_flos": 155170897920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null