Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1051d91e2052985f39311e2d2ed8de4b80e25626573e232c1224ee684a19b5ce
+oid sha256:cfd117b45dd7be8a2d260dcb6fbda93f8eeda8e441856d1493b92884f47168cb
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3414ea31e162597700d697fb8d922a3448230b9bb9d56d02e6fa16c51df54b82
+oid sha256:48afe9a81c135b45bf08b4710b7f165644175fef1bf8e9e49009cdd65bde8d3e
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bcae1ac656473ea59460f67289f079882df210eef5f64855bbdb5999f8f24da
+oid sha256:1ed7ca119b1bf30b84e2a47e7f17ceb2248570daa1816b394db964ee75ab45ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006518267444513249,
+  "epoch": 0.009777401166769872,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 19.354,
       "eval_steps_per_second": 9.677,
       "step": 100
+    },
+    {
+      "epoch": 0.007170094188964573,
+      "grad_norm": 0.9510365128517151,
+      "learning_rate": 0.0002,
+      "loss": 1.6355,
+      "step": 110
+    },
+    {
+      "epoch": 0.007821920933415898,
+      "grad_norm": 0.7684184312820435,
+      "learning_rate": 0.0002,
+      "loss": 1.6816,
+      "step": 120
+    },
+    {
+      "epoch": 0.008473747677867223,
+      "grad_norm": 0.7511278390884399,
+      "learning_rate": 0.0002,
+      "loss": 1.7392,
+      "step": 130
+    },
+    {
+      "epoch": 0.009125574422318547,
+      "grad_norm": 1.2092989683151245,
+      "learning_rate": 0.0002,
+      "loss": 1.5957,
+      "step": 140
+    },
+    {
+      "epoch": 0.009777401166769872,
+      "grad_norm": 0.7998082041740417,
+      "learning_rate": 0.0002,
+      "loss": 1.5553,
+      "step": 150
+    },
+    {
+      "epoch": 0.009777401166769872,
+      "eval_loss": 1.726781964302063,
+      "eval_runtime": 333.6825,
+      "eval_samples_per_second": 19.36,
+      "eval_steps_per_second": 9.68,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.211454122668851e+16,
+  "total_flos": 3.3248776600682496e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null