Training in progress, step 102, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4a3e12ace7db54eb920b934f6c0ee05cc4f4a8c194adf5d5df9e3b0cdd68c9
+oid sha256:be35ee36755478e76a6f4ad9db283dac6d2eb1a117f15b7c878f4bd414dd2feb
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bedc55c1f8f18184593c54334179fa1f18a4e48f30fc591992b4c57dd36d69e
+oid sha256:26dc26a33c15a18b360aa7a53225e04ab4eaa8b9255524cb6abac713731bbb76
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81be7588d13c4d18f0badc374dddf114640e4f47aaffe28b0dd04921466a3ad
+oid sha256:a6c0c3b8743a7e8d1ccbd11d11a82d7e1b52534db8cb37208129f7a94751cd17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24510621ac929102038dbb9557bac0e17f0ed52c36608ebab8e700d1b1464f1d
+oid sha256:fcbdf5cce354397b1cc7dbc75ae72cd1ce74fbf84991f656a8ae8c5ec4cf6c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4689655172413793,
+  "epoch": 0.5627586206896552,
   "eval_steps": 17,
-  "global_step": 85,
+  "global_step": 102,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -251,6 +251,56 @@
       "eval_samples_per_second": 68.623,
       "eval_steps_per_second": 8.775,
       "step": 85
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5210072994232178,
+      "learning_rate": 6.466250186922325e-05,
+      "loss": 2.006,
+      "step": 87
+    },
+    {
+      "epoch": 0.496551724137931,
+      "grad_norm": 0.4956110119819641,
+      "learning_rate": 6.227427435703997e-05,
+      "loss": 2.0443,
+      "step": 90
+    },
+    {
+      "epoch": 0.5131034482758621,
+      "grad_norm": 0.5796875357627869,
+      "learning_rate": 5.985585137257401e-05,
+      "loss": 2.173,
+      "step": 93
+    },
+    {
+      "epoch": 0.5296551724137931,
+      "grad_norm": 0.5329291224479675,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 2.1224,
+      "step": 96
+    },
+    {
+      "epoch": 0.5462068965517242,
+      "grad_norm": 0.555596113204956,
+      "learning_rate": 5.495227651252315e-05,
+      "loss": 2.0329,
+      "step": 99
+    },
+    {
+      "epoch": 0.5627586206896552,
+      "grad_norm": 0.462854266166687,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 1.9292,
+      "step": 102
+    },
+    {
+      "epoch": 0.5627586206896552,
+      "eval_loss": 2.1433825492858887,
+      "eval_runtime": 4.4422,
+      "eval_samples_per_second": 68.66,
+      "eval_steps_per_second": 8.779,
+      "step": 102
     }
   ],
   "logging_steps": 3,
@@ -270,7 +320,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5403198986649600.0,
+  "total_flos": 6483838783979520.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null