Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d40e4bd4360c7ea818536775609f99123bd7fc3a3244121d95b9fa02b4df175
+oid sha256:43aa59b6039959e35571efed99f957fb3afce710e87f6874944df9731ed6b77d
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ddb980ccfda29093b261858f2bb6f06f2cd317ecc3e1c7dab5fb5d932f7a5d2
+oid sha256:c673e5e854dd6049a13737a6d10765a36451bd3b485c7f0fa91cb5a821ecb390
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd11c0e5fa567a288a3e7fc5c47f799160ad0c2656a839e3b49ff66725e523e2
+oid sha256:c7332cedcc7b3b36b7974e070bd9fa7171e6a96e191919b27b6014d872048e1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0031573131265293236,
+  "epoch": 0.006314626253058647,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 5.399,
       "eval_steps_per_second": 2.699,
       "step": 10
+    },
+    {
+      "epoch": 0.003788775751835188,
+      "grad_norm": 1.6175545454025269,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.7124,
+      "step": 12
+    },
+    {
+      "epoch": 0.004735969689793985,
+      "grad_norm": 2.217756986618042,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.0008,
+      "step": 15
+    },
+    {
+      "epoch": 0.004735969689793985,
+      "eval_loss": 1.4084513187408447,
+      "eval_runtime": 247.059,
+      "eval_samples_per_second": 5.4,
+      "eval_steps_per_second": 2.7,
+      "step": 15
+    },
+    {
+      "epoch": 0.005683163627752783,
+      "grad_norm": 2.475426435470581,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.6367,
+      "step": 18
+    },
+    {
+      "epoch": 0.006314626253058647,
+      "eval_loss": 1.2930963039398193,
+      "eval_runtime": 246.796,
+      "eval_samples_per_second": 5.405,
+      "eval_steps_per_second": 2.703,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347829962342400.0,
+  "total_flos": 1.26956599246848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null