Training in progress, step 136, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbf1eca6e8a077aad44f0eea548900906563fba91ae629ff999cfbb84d12183
+oid sha256:8d49930c00528f90da24b6b608e7e80bf7ca0b3683118ac70ed158a02ed82355
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c50059bf06051c0e59a9446ee43b11917461b9915373cdac8ef7e15a1c3f0d
+oid sha256:bc94d5b33f89c7421164351f9effdc622887a5194f3ac924e62ab147d4f6ce73
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455d3b76f5d818e204f559cce8a72f513e0e5623eb82e10af57277665f41a7cb
+oid sha256:dd821849c8a72b596e3334c93cfab0767818edfb3fd7124c4efcd8a0829df152
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baea37709b071cdabc5712824dc3f783ecd30d18a1e0d85c4d56cfebfa22b7e0
+oid sha256:2f676b917baa0a895f62d4ea12d985f19fe259f840a0ba6d41d00cece68314f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02900199033266989,
+  "epoch": 0.038669320443559856,
   "eval_steps": 34,
-  "global_step": 102,
+  "global_step": 136,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,91 @@
       "eval_samples_per_second": 35.248,
       "eval_steps_per_second": 4.409,
       "step": 102
+    },
+    {
+      "epoch": 0.029854990048336652,
+      "grad_norm": 0.2670081853866577,
+      "learning_rate": 4.303006118359537e-05,
+      "loss": 0.8789,
+      "step": 105
+    },
+    {
+      "epoch": 0.03070798976400341,
+      "grad_norm": 0.3037591874599457,
+      "learning_rate": 4.260632628966974e-05,
+      "loss": 0.8526,
+      "step": 108
+    },
+    {
+      "epoch": 0.031560989479670176,
+      "grad_norm": 0.28440290689468384,
+      "learning_rate": 4.217230979699188e-05,
+      "loss": 0.8274,
+      "step": 111
+    },
+    {
+      "epoch": 0.03241398919533694,
+      "grad_norm": 0.49433842301368713,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.8104,
+      "step": 114
+    },
+    {
+      "epoch": 0.03326698891100369,
+      "grad_norm": 0.2911880314350128,
+      "learning_rate": 4.12744516851726e-05,
+      "loss": 0.8392,
+      "step": 117
+    },
+    {
+      "epoch": 0.034119988626670456,
+      "grad_norm": 0.3204285502433777,
+      "learning_rate": 4.0811134389884433e-05,
+      "loss": 0.788,
+      "step": 120
+    },
+    {
+      "epoch": 0.03497298834233722,
+      "grad_norm": 0.35650599002838135,
+      "learning_rate": 4.0338583837360225e-05,
+      "loss": 0.8004,
+      "step": 123
+    },
+    {
+      "epoch": 0.03582598805800398,
+      "grad_norm": 0.310162216424942,
+      "learning_rate": 3.985707598381544e-05,
+      "loss": 0.8085,
+      "step": 126
+    },
+    {
+      "epoch": 0.03667898777367074,
+      "grad_norm": 0.3370768129825592,
+      "learning_rate": 3.9366892016277096e-05,
+      "loss": 0.7317,
+      "step": 129
+    },
+    {
+      "epoch": 0.037531987489337504,
+      "grad_norm": 0.4600171446800232,
+      "learning_rate": 3.886831818837847e-05,
+      "loss": 0.7626,
+      "step": 132
+    },
+    {
+      "epoch": 0.038384987205004266,
+      "grad_norm": 0.43600377440452576,
+      "learning_rate": 3.8361645653195026e-05,
+      "loss": 0.7679,
+      "step": 135
+    },
+    {
+      "epoch": 0.038669320443559856,
+      "eval_loss": 0.7138456106185913,
+      "eval_runtime": 168.0686,
+      "eval_samples_per_second": 35.248,
+      "eval_steps_per_second": 4.409,
+      "step": 136
     }
   ],
   "logging_steps": 3,
@@ -296,7 +381,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2664001796112384e+16,
+  "total_flos": 4.355200239481651e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null