Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c4471d4c9cb64d09a6a7b30ac9acaaee7bcb2ad736e42b5cae06ec31ff4d3a
+oid sha256:45be0444a9dc1f18e973e9f89b2937e2959c7e6b0ef994e882a6135a2a5dfff5
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce7a8feea41db270f56d340882d0d3416c58bd18cc1b291769b71a91d463cd0f
+oid sha256:b2f3d88370ab7afb489f5413e608e38819180f5d6acfccf51ced90c1502d882f
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63f4f0d73cfa12954b18866e2bc71834d7bd1e65711fb8787e02fc9fa799dbae
+oid sha256:adcd44ae0738a9f5253da9c80771d2b2792c07a8668a338ec887b78d8a8344b2
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20095ae7e248e019efdc0c5bbc6d09f2da8b05d1a427b4f2fe08d3ff1ff17a2
+oid sha256:d7535ce96425be73a04023e89f81a4c8570ef09d5226d185278d9ff2553f8529
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.39637922820390664,
+  "epoch": 0.5945688423058599,
   "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": 39.25,
       "eval_steps_per_second": 9.857,
       "step": 26
+    },
+    {
+      "epoch": 0.4116245831348261,
+      "grad_norm": 0.16044408082962036,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9902,
+      "step": 27
+    },
+    {
+      "epoch": 0.4268699380657456,
+      "grad_norm": 0.16952988505363464,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.95,
+      "step": 28
+    },
+    {
+      "epoch": 0.4421152929966651,
+      "grad_norm": 0.17723830044269562,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.967,
+      "step": 29
+    },
+    {
+      "epoch": 0.4573606479275846,
+      "grad_norm": 0.15307919681072235,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9555,
+      "step": 30
+    },
+    {
+      "epoch": 0.47260600285850407,
+      "grad_norm": 0.14987881481647491,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.962,
+      "step": 31
+    },
+    {
+      "epoch": 0.4878513577894235,
+      "grad_norm": 0.1537853628396988,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9771,
+      "step": 32
+    },
+    {
+      "epoch": 0.5030967127203431,
+      "grad_norm": 0.14937259256839752,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9698,
+      "step": 33
+    },
+    {
+      "epoch": 0.5183420676512626,
+      "grad_norm": 0.14822566509246826,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.939,
+      "step": 34
+    },
+    {
+      "epoch": 0.533587422582182,
+      "grad_norm": 0.1477845311164856,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9362,
+      "step": 35
+    },
+    {
+      "epoch": 0.5488327775131014,
+      "grad_norm": 0.1507962942123413,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9757,
+      "step": 36
+    },
+    {
+      "epoch": 0.5640781324440209,
+      "grad_norm": 0.14477087557315826,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9762,
+      "step": 37
+    },
+    {
+      "epoch": 0.5793234873749404,
+      "grad_norm": 0.14497476816177368,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9458,
+      "step": 38
+    },
+    {
+      "epoch": 0.5945688423058599,
+      "grad_norm": 0.1580241322517395,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9517,
+      "step": 39
+    },
+    {
+      "epoch": 0.5945688423058599,
+      "eval_loss": 0.9688416719436646,
+      "eval_runtime": 11.2667,
+      "eval_samples_per_second": 39.23,
+      "eval_steps_per_second": 9.852,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.56434818332754e+16,
+  "total_flos": 1.2846522274991309e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null