Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45416d00ceb9b99ea16a8813089ab2663461ee123db1ac9fb02a80f85a6ac28
+oid sha256:d784918062809adab38d96de73f8a6d2307264464c9e6c99ab5be25c60e0edbe
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a41b22f293c5d3d5525e668792c3c36268bd5ede49f52a93b30a3163e29d2bad
+oid sha256:d2bc455574310189264c1525868c247f17b1070d3b25cebddf4376471c345062
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8304ec2a6d17f2fb653a1abf760827f721a8a13ddb8623cc2b6b1db9cafc28e1
+oid sha256:52fccfd1b8c54400836b1f560133e9fc50af3ddebc0615ff28398e1e5ce887a9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6314c20cf33c3475e02118fdd5b3e20b87c872ae889966547e2d23f9a2c9edd0
+oid sha256:18259e58314b4ea7c9ab8ed785bce4c4419596e28db8bdd64430783ae4aeb12f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e37c8a0102bf8bacfc20068740d4a4ac15d3805538fe41d198bc03e0943b164
+oid sha256:1321fcddcaa70421d5a753abe41bad66ade5e0871a2c553d195d0cd4d6e82f1f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4455397219f239cb0cdc4448b8b424c6537da38b0aea02b9e3831bbac98b9952
+oid sha256:1fa7a33c3153f16e6bfcfb08f11291e21413db226de6dbe812e1786bdfc5a482
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19047619047619047,
+  "epoch": 0.2857142857142857,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 2.1279,
       "step": 50
+    },
+    {
+      "epoch": 0.19428571428571428,
+      "grad_norm": 0.532867968082428,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.1911,
+      "step": 51
+    },
+    {
+      "epoch": 0.1980952380952381,
+      "grad_norm": 0.6397295594215393,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.1223,
+      "step": 52
+    },
+    {
+      "epoch": 0.2019047619047619,
+      "grad_norm": 0.6476990580558777,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.1393,
+      "step": 53
+    },
+    {
+      "epoch": 0.2057142857142857,
+      "grad_norm": 1.3416658639907837,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.2902,
+      "step": 54
+    },
+    {
+      "epoch": 0.2057142857142857,
+      "eval_loss": 2.222794771194458,
+      "eval_runtime": 23.4201,
+      "eval_samples_per_second": 37.745,
+      "eval_steps_per_second": 1.196,
+      "step": 54
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "grad_norm": 0.6062219142913818,
+      "learning_rate": 5e-05,
+      "loss": 2.2142,
+      "step": 55
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.531572163105011,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.1585,
+      "step": 56
+    },
+    {
+      "epoch": 0.21714285714285714,
+      "grad_norm": 0.5543264746665955,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.2081,
+      "step": 57
+    },
+    {
+      "epoch": 0.22095238095238096,
+      "grad_norm": 0.9360385537147522,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.0396,
+      "step": 58
+    },
+    {
+      "epoch": 0.22476190476190477,
+      "grad_norm": 0.6253273487091064,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 2.2449,
+      "step": 59
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.6404938697814941,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.2385,
+      "step": 60
+    },
+    {
+      "epoch": 0.23238095238095238,
+      "grad_norm": 0.6263427138328552,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.1528,
+      "step": 61
+    },
+    {
+      "epoch": 0.2361904761904762,
+      "grad_norm": 0.7024621963500977,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.2712,
+      "step": 62
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.5970602631568909,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.1885,
+      "step": 63
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 2.220242977142334,
+      "eval_runtime": 23.4283,
+      "eval_samples_per_second": 37.732,
+      "eval_steps_per_second": 1.195,
+      "step": 63
+    },
+    {
+      "epoch": 0.2438095238095238,
+      "grad_norm": 0.631573498249054,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.2119,
+      "step": 64
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "grad_norm": 0.6913384795188904,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.1587,
+      "step": 65
+    },
+    {
+      "epoch": 0.25142857142857145,
+      "grad_norm": 0.6332992911338806,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.1551,
+      "step": 66
+    },
+    {
+      "epoch": 0.25523809523809526,
+      "grad_norm": 0.6200920939445496,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 2.1621,
+      "step": 67
+    },
+    {
+      "epoch": 0.259047619047619,
+      "grad_norm": 0.623578667640686,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.1721,
+      "step": 68
+    },
+    {
+      "epoch": 0.26285714285714284,
+      "grad_norm": 0.5753321051597595,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.298,
+      "step": 69
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.7991951704025269,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1777,
+      "step": 70
+    },
+    {
+      "epoch": 0.2704761904761905,
+      "grad_norm": 0.6142107248306274,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.236,
+      "step": 71
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "grad_norm": 0.5913622379302979,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2797,
+      "step": 72
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "eval_loss": 2.2107057571411133,
+      "eval_runtime": 23.4571,
+      "eval_samples_per_second": 37.686,
+      "eval_steps_per_second": 1.194,
+      "step": 72
+    },
+    {
+      "epoch": 0.2780952380952381,
+      "grad_norm": 0.5493815541267395,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.1707,
+      "step": 73
+    },
+    {
+      "epoch": 0.2819047619047619,
+      "grad_norm": 7.019804000854492,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.0899,
+      "step": 74
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.6025744676589966,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.1821,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.967549134241792e+17,
+  "total_flos": 4.451323701362688e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null