Training in progress, step 117, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c8aa53823ec3979ff7e1d30c047e5acabcd3fa8498d84f6505bf010dca950e
+oid sha256:c5798fb376cb521b651dd28099ce2c086647fdcbbb595c40f31e09f0bca4fabf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96de6f303d3e97c3b7742b2a9b1b32fd5b6504ff4598532cec8774dd143d3b3f
+oid sha256:47df0430f355abf76b457d4820080696300cbebbc336555910b86ea1f907aefe
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:907075ac1b403dbc4ff0a0072e837127222d83d6490ad3ff06d167e2f6175a5e
+oid sha256:70bd3f5a04474750befb510a828eb2569e420cfa0abc940751ff6ccd74605249
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea77b645dadc8ac2aadc6fa983d5a64d4e6a08d5eac1b852910f8408f0833c7
+oid sha256:96bbb5cc30267ffbb6fcba5b12ec3b2b908df1e2e422c7d381d682f082ea4159
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11754732975416785,
+  "epoch": 0.13224074597343882,
   "eval_steps": 13,
-  "global_step": 104,
+  "global_step": 117,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -317,6 +317,49 @@
       "eval_samples_per_second": 6.62,
       "eval_steps_per_second": 0.831,
       "step": 104
+    },
+    {
+      "epoch": 0.11867759254026561,
+      "grad_norm": 1.0611317157745361,
+      "learning_rate": 1.1699198087116589e-05,
+      "loss": 0.5579,
+      "step": 105
+    },
+    {
+      "epoch": 0.12206838089855891,
+      "grad_norm": 1.7777539491653442,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.5391,
+      "step": 108
+    },
+    {
+      "epoch": 0.12545916925685222,
+      "grad_norm": 1.0344315767288208,
+      "learning_rate": 8.978109650374397e-06,
+      "loss": 0.4931,
+      "step": 111
+    },
+    {
+      "epoch": 0.12884995761514553,
+      "grad_norm": 1.0285758972167969,
+      "learning_rate": 7.723433775328384e-06,
+      "loss": 0.5289,
+      "step": 114
+    },
+    {
+      "epoch": 0.13224074597343882,
+      "grad_norm": 0.9961230158805847,
+      "learning_rate": 6.547025062816486e-06,
+      "loss": 0.5086,
+      "step": 117
+    },
+    {
+      "epoch": 0.13224074597343882,
+      "eval_loss": 0.12818647921085358,
+      "eval_runtime": 224.9913,
+      "eval_samples_per_second": 6.622,
+      "eval_steps_per_second": 0.831,
+      "step": 117
     }
   ],
   "logging_steps": 3,
@@ -336,7 +379,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.925022064588882e+17,
+  "total_flos": 3.290649822662492e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null