Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c5726baa7de3e8afd59b201515892c486d5172c9ec6ea12dff4da33cb979b6
+oid sha256:261f8727997945eb87e0bb82facc9b388349955b33cdb62b6807af15ec1fdceb
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47b1ec98f4b0bee92c11b84853dc1756dadfa77499fe2a6d647f5d5f0420b3a0
+oid sha256:a6c1e6436794826f46c90dbc8a3888e0168b34c222f452abc2c1e417b5fed11c
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602fb08d1680b53d6bd33a99882ac9da2eca9540b980d41f3e3fe7abb49c54f9
+oid sha256:682fa06fe8ef6e09ffdeef985646187c38172ce94e6a1d0b34ec5f6df8451d9d
 size 14244

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": 0.17185821697099893,
+  "epoch": 0.2577873254564984,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,181 @@
       "eval_samples_per_second": 29.26,
       "eval_steps_per_second": 29.26,
       "step": 50
+    },
+    {
+      "epoch": 0.1752953813104189,
+      "grad_norm": 0.3440859317779541,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.2643,
+      "step": 51
+    },
+    {
+      "epoch": 0.17873254564983887,
+      "grad_norm": 0.3143952488899231,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.3741,
+      "step": 52
+    },
+    {
+      "epoch": 0.18216970998925885,
+      "grad_norm": 0.5445249676704407,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.3737,
+      "step": 53
+    },
+    {
+      "epoch": 0.18560687432867884,
+      "grad_norm": 0.29417288303375244,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.2626,
+      "step": 54
+    },
+    {
+      "epoch": 0.18904403866809882,
+      "grad_norm": 0.2821301519870758,
+      "learning_rate": 5e-05,
+      "loss": 2.2226,
+      "step": 55
+    },
+    {
+      "epoch": 0.1924812030075188,
+      "grad_norm": 0.5049765706062317,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2056,
+      "step": 56
+    },
+    {
+      "epoch": 0.19591836734693877,
+      "grad_norm": 0.2741824984550476,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.0916,
+      "step": 57
+    },
+    {
+      "epoch": 0.19935553168635875,
+      "grad_norm": 0.2932296097278595,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.1948,
+      "step": 58
+    },
+    {
+      "epoch": 0.20279269602577873,
+      "grad_norm": 0.2703547477722168,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 2.2377,
+      "step": 59
+    },
+    {
+      "epoch": 0.20622986036519872,
+      "grad_norm": 0.5145007371902466,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.2336,
+      "step": 60
+    },
+    {
+      "epoch": 0.20966702470461868,
+      "grad_norm": 0.3122769594192505,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.1879,
+      "step": 61
+    },
+    {
+      "epoch": 0.21310418904403866,
+      "grad_norm": 0.2763988673686981,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.2149,
+      "step": 62
+    },
+    {
+      "epoch": 0.21654135338345865,
+      "grad_norm": 0.31647786498069763,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.1863,
+      "step": 63
+    },
+    {
+      "epoch": 0.21997851772287863,
+      "grad_norm": 0.5407307744026184,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.2516,
+      "step": 64
+    },
+    {
+      "epoch": 0.22341568206229862,
+      "grad_norm": 0.31190451979637146,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.2059,
+      "step": 65
+    },
+    {
+      "epoch": 0.22685284640171857,
+      "grad_norm": 0.3045297861099243,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2161,
+      "step": 66
+    },
+    {
+      "epoch": 0.23029001074113856,
+      "grad_norm": 0.3111981153488159,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 2.2722,
+      "step": 67
+    },
+    {
+      "epoch": 0.23372717508055854,
+      "grad_norm": 0.5072479844093323,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.1672,
+      "step": 68
+    },
+    {
+      "epoch": 0.23716433941997853,
+      "grad_norm": 0.4372091293334961,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.3158,
+      "step": 69
+    },
+    {
+      "epoch": 0.24060150375939848,
+      "grad_norm": 0.28215134143829346,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2365,
+      "step": 70
+    },
+    {
+      "epoch": 0.24403866809881847,
+      "grad_norm": 0.3402535915374756,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.2135,
+      "step": 71
+    },
+    {
+      "epoch": 0.24747583243823845,
+      "grad_norm": 0.46998509764671326,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.3625,
+      "step": 72
+    },
+    {
+      "epoch": 0.25091299677765844,
+      "grad_norm": 0.2795167565345764,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.1809,
+      "step": 73
+    },
+    {
+      "epoch": 0.2543501611170784,
+      "grad_norm": 0.37644481658935547,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.2632,
+      "step": 74
+    },
+    {
+      "epoch": 0.2577873254564984,
+      "grad_norm": 0.32024654746055603,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.2528,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -392,7 +567,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1068216062312448.0,
+  "total_flos": 1619041760575488.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null