Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b50ec8140e48761f8c8b1a9df445df04a3c73695f32a6b4b054698343e9fac3
+oid sha256:91c4efd86d4f806c6bd015bc91268c34751c8ea13e3481b867ccdc373235cf51
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e982664d5160c48018b69543565ed66b637440e00f4df9272f1f34de7d6856
+oid sha256:a0cf038d141305206d5d9c29e6517433b96721e964a4d8c495f4b8b8c9fb8a31
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27551e93507b1ff29df93e470e140f6063fd7ad4c97890508b3255a144275920
+oid sha256:cd0e9045183916a77f191421cff82618df77003ceaa3909e936c6fdd5d3e7edd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015035419979760012,
+  "epoch": 0.022553129969640016,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 29.547,
       "eval_steps_per_second": 14.794,
       "step": 26
+    },
+    {
+      "epoch": 0.015613705363596936,
+      "grad_norm": 0.5554443597793579,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.6288,
+      "step": 27
+    },
+    {
+      "epoch": 0.016191990747433858,
+      "grad_norm": 0.6648669838905334,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.6552,
+      "step": 28
+    },
+    {
+      "epoch": 0.016770276131270783,
+      "grad_norm": 0.728183925151825,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.6793,
+      "step": 29
+    },
+    {
+      "epoch": 0.017348561515107705,
+      "grad_norm": 0.5944912433624268,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6537,
+      "step": 30
+    },
+    {
+      "epoch": 0.01792684689894463,
+      "grad_norm": 0.6181674599647522,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.6846,
+      "step": 31
+    },
+    {
+      "epoch": 0.018505132282781552,
+      "grad_norm": 0.8404297232627869,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.7196,
+      "step": 32
+    },
+    {
+      "epoch": 0.019083417666618478,
+      "grad_norm": 0.706020176410675,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.6079,
+      "step": 33
+    },
+    {
+      "epoch": 0.0196617030504554,
+      "grad_norm": 0.7011454701423645,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.7039,
+      "step": 34
+    },
+    {
+      "epoch": 0.020239988434292325,
+      "grad_norm": 0.6933149695396423,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.6284,
+      "step": 35
+    },
+    {
+      "epoch": 0.020818273818129247,
+      "grad_norm": 0.7218239903450012,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.6569,
+      "step": 36
+    },
+    {
+      "epoch": 0.021396559201966172,
+      "grad_norm": 0.7234783172607422,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.6429,
+      "step": 37
+    },
+    {
+      "epoch": 0.021974844585803094,
+      "grad_norm": 0.5774780511856079,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.5611,
+      "step": 38
+    },
+    {
+      "epoch": 0.022553129969640016,
+      "grad_norm": 0.7207251191139221,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.6489,
+      "step": 39
+    },
+    {
+      "epoch": 0.022553129969640016,
+      "eval_loss": 0.6252636909484863,
+      "eval_runtime": 24.6955,
+      "eval_samples_per_second": 29.52,
+      "eval_steps_per_second": 14.78,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4993823469993984.0,
+  "total_flos": 7536974311194624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null