Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:079c25328b181d5c3f3c75a84883db652e25c67b3ffd0f7d39042826b1cce025
+oid sha256:0e6c315b39d443cc773c362027346865cb3cd9024065a68da192d469b8027cb1
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9173ea5cd107abc40ddcc64656dbdc3535ddca00307a69a6ed28d3f37a1b44c
+oid sha256:6d69ecd8a76ea16e1ade4b800f7e970f6171e96e8aa2410283e76d8ffc37c95a
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95544619e944677abbfd466e75ed51a77c348214581301e911257e4ca349e97e
+oid sha256:a30ab6aba457b62b3b46ef063f965a22dbd99e339a0860a0336ca542d741ea12
 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": 0.06471686372121967,
+  "epoch": 0.0970752955818295,
   "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": 13.183,
       "eval_steps_per_second": 6.592,
       "step": 26
+    },
+    {
+      "epoch": 0.0672059738643435,
+      "grad_norm": 0.7916014790534973,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 5.0277,
+      "step": 27
+    },
+    {
+      "epoch": 0.06969508400746734,
+      "grad_norm": 0.8039388656616211,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 4.7928,
+      "step": 28
+    },
+    {
+      "epoch": 0.07218419415059116,
+      "grad_norm": 0.8315812945365906,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 4.7905,
+      "step": 29
+    },
+    {
+      "epoch": 0.07467330429371499,
+      "grad_norm": 0.8699222207069397,
+      "learning_rate": 2.5e-05,
+      "loss": 4.8264,
+      "step": 30
+    },
+    {
+      "epoch": 0.07716241443683883,
+      "grad_norm": 0.8263019323348999,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 4.6388,
+      "step": 31
+    },
+    {
+      "epoch": 0.07965152457996266,
+      "grad_norm": 0.8435355424880981,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 4.7284,
+      "step": 32
+    },
+    {
+      "epoch": 0.0821406347230865,
+      "grad_norm": 0.8042365908622742,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 4.4383,
+      "step": 33
+    },
+    {
+      "epoch": 0.08462974486621033,
+      "grad_norm": 0.8197401762008667,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 4.4689,
+      "step": 34
+    },
+    {
+      "epoch": 0.08711885500933417,
+      "grad_norm": 0.8895244002342224,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 4.6372,
+      "step": 35
+    },
+    {
+      "epoch": 0.089607965152458,
+      "grad_norm": 0.8460880517959595,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 4.324,
+      "step": 36
+    },
+    {
+      "epoch": 0.09209707529558182,
+      "grad_norm": 0.885506272315979,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 4.7796,
+      "step": 37
+    },
+    {
+      "epoch": 0.09458618543870566,
+      "grad_norm": 0.8955153822898865,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 4.5446,
+      "step": 38
+    },
+    {
+      "epoch": 0.0970752955818295,
+      "grad_norm": 0.8827160000801086,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 4.483,
+      "step": 39
+    },
+    {
+      "epoch": 0.0970752955818295,
+      "eval_loss": 1.1446497440338135,
+      "eval_runtime": 12.9134,
+      "eval_samples_per_second": 13.165,
+      "eval_steps_per_second": 6.582,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.631409068310528e+16,
+  "total_flos": 2.447113602465792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null