Training in progress, step 105, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2804ca5b5892a76645bfd34d9388ae43f9efcfd8d9f15335cdc723c5a0fed53b
+oid sha256:c0507935a7a5988872cc5772dcb294e52b7fc5546cbc61ad4bb82746897b3cea
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b279f97477546bd8157a8dce653efa9e4e2aac00a9e7a0101b5793489729d25
+oid sha256:5e0875e2466f8ff77e67e7f868d827dae957f935b2fedd14ae4398a4509f9671
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a9b6b38714cd4775330d5c8485f5a42057200cf2746b572faa0571796877a3
+oid sha256:644ee7a407ff427bfff48d3e44599fd4c3c1f87d2e4236f5b837a5a70e456336
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b8a5b9aaab52c529e8225a8efdb5ee4b1c103decfe1101828eac45305d759c
+oid sha256:e8c855c846898181ed358c1ef65b19ad1435172d9025fde7f25f4580bfc48faa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04890274466654441,
+  "epoch": 0.051347881899871634,
   "eval_steps": 34,
-  "global_step": 100,
+  "global_step": 105,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,49 @@
       "learning_rate": 0.0001273662990072083,
       "loss": 8.2901,
       "step": 100
+    },
+    {
+      "epoch": 0.04939177211320985,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012558427775944357,
+      "loss": 8.3534,
+      "step": 101
+    },
+    {
+      "epoch": 0.049880799559875295,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012379351950426187,
+      "loss": 9.2843,
+      "step": 102
+    },
+    {
+      "epoch": 0.049880799559875295,
+      "eval_loss": 8.778116226196289,
+      "eval_runtime": 879.772,
+      "eval_samples_per_second": 2.936,
+      "eval_steps_per_second": 0.979,
+      "step": 102
+    },
+    {
+      "epoch": 0.05036982700654074,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012199463578396688,
+      "loss": 8.6895,
+      "step": 103
+    },
+    {
+      "epoch": 0.05085885445320618,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012018824091570103,
+      "loss": 7.7172,
+      "step": 104
+    },
+    {
+      "epoch": 0.051347881899871634,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00011837495178165706,
+      "loss": 8.9099,
+      "step": 105
     }
   ],
   "logging_steps": 1,
@@ -750,7 +793,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.204479675957248e+17,
+  "total_flos": 2.3147036597551104e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null