Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50586fd2411260afc18a5140eb6eec2a0bcfb632a87c78de61b684cf071fbaf5
+oid sha256:a31a542e2dbb2c9cbe799386642c1e0b77dc5941a765201ea34a5511bc04ab63
 size 479769104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca84a8847e1ee6be02ac936fcc1af3d1de40cc5f56ad51604ebd3fc04fb1dbe
+oid sha256:1ed5cc0419647052fd30648d8c3078b7b3cb31f218b1103a547918cea2f1358f
 size 240728084

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289a7023689774a52b1b13bddd72584da17e89c0b2ac881739dc070a2b1f637f
+oid sha256:85b7a108a3eca8766b6cabea067222bf8fc5ccd85d84371fb8aa5547b4f34b95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010344207546826732,
+  "epoch": 0.0020688415093653464,
   "eval_steps": 500,
-  "global_step": 16,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,118 @@
       "learning_rate": 1.0322580645161291e-06,
       "loss": 1.6359,
       "step": 16
+    },
+    {
+      "epoch": 0.0010990720518503404,
+      "grad_norm": 25.75543785095215,
+      "learning_rate": 1.0967741935483872e-06,
+      "loss": 1.6014,
+      "step": 17
+    },
+    {
+      "epoch": 0.0011637233490180074,
+      "grad_norm": 11.885198593139648,
+      "learning_rate": 1.1612903225806454e-06,
+      "loss": 1.6831,
+      "step": 18
+    },
+    {
+      "epoch": 0.0012283746461856746,
+      "grad_norm": 14.924345016479492,
+      "learning_rate": 1.2258064516129033e-06,
+      "loss": 1.7223,
+      "step": 19
+    },
+    {
+      "epoch": 0.0012930259433533416,
+      "grad_norm": 18.01887321472168,
+      "learning_rate": 1.2903225806451614e-06,
+      "loss": 1.6811,
+      "step": 20
+    },
+    {
+      "epoch": 0.0013576772405210086,
+      "grad_norm": 12.34964656829834,
+      "learning_rate": 1.3548387096774195e-06,
+      "loss": 1.6169,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014223285376886757,
+      "grad_norm": 11.162965774536133,
+      "learning_rate": 1.4193548387096776e-06,
+      "loss": 1.6814,
+      "step": 22
+    },
+    {
+      "epoch": 0.0014869798348563427,
+      "grad_norm": 8.694445610046387,
+      "learning_rate": 1.4838709677419356e-06,
+      "loss": 1.5999,
+      "step": 23
+    },
+    {
+      "epoch": 0.00155163113202401,
+      "grad_norm": 9.510068893432617,
+      "learning_rate": 1.5483870967741937e-06,
+      "loss": 1.6327,
+      "step": 24
+    },
+    {
+      "epoch": 0.001616282429191677,
+      "grad_norm": 9.788911819458008,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 1.6985,
+      "step": 25
+    },
+    {
+      "epoch": 0.001680933726359344,
+      "grad_norm": 8.04429817199707,
+      "learning_rate": 1.67741935483871e-06,
+      "loss": 1.6618,
+      "step": 26
+    },
+    {
+      "epoch": 0.001745585023527011,
+      "grad_norm": 7.545624256134033,
+      "learning_rate": 1.7419354838709678e-06,
+      "loss": 1.5472,
+      "step": 27
+    },
+    {
+      "epoch": 0.0018102363206946783,
+      "grad_norm": 7.069305419921875,
+      "learning_rate": 1.8064516129032258e-06,
+      "loss": 1.643,
+      "step": 28
+    },
+    {
+      "epoch": 0.0018748876178623453,
+      "grad_norm": 9.195314407348633,
+      "learning_rate": 1.870967741935484e-06,
+      "loss": 1.5956,
+      "step": 29
+    },
+    {
+      "epoch": 0.0019395389150300122,
+      "grad_norm": 6.884894371032715,
+      "learning_rate": 1.935483870967742e-06,
+      "loss": 1.5752,
+      "step": 30
+    },
+    {
+      "epoch": 0.0020041902121976794,
+      "grad_norm": 7.165380477905273,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.5812,
+      "step": 31
+    },
+    {
+      "epoch": 0.0020688415093653464,
+      "grad_norm": 6.563286781311035,
+      "learning_rate": 2.0645161290322582e-06,
+      "loss": 1.5938,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -138,7 +250,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9899397096579072.0,
+  "total_flos": 2.068879221404467e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null