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:dbbd7965ad10a8bb712cb3b13e0f5394f019c595b19c66fd63ec7e4f9b2c4ac7
+oid sha256:d4aea84b647ebd715e2b1bf794ffac76710716da5f27a47b9a79e7e8558520cc
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02a890e7ddd1340e75f40064bc8e5ddbab44eb3b7fe7131b184f262c48e076c
+oid sha256:e0489febcfb7b118c2ff7102ddb7772e23500724c5891bf6a31e8b47c12a0c24
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
+oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
 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": 0.008595495960116899,
+  "epoch": 0.012893243940175348,
   "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": 3.8653,
       "step": 50
+    },
+    {
+      "epoch": 0.008767405879319236,
+      "grad_norm": 1.7195965051651,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 3.8959,
+      "step": 51
+    },
+    {
+      "epoch": 0.008939315798521575,
+      "grad_norm": 1.5374380350112915,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 3.8239,
+      "step": 52
+    },
+    {
+      "epoch": 0.009111225717723912,
+      "grad_norm": 1.6469768285751343,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 3.6301,
+      "step": 53
+    },
+    {
+      "epoch": 0.009283135636926251,
+      "grad_norm": 1.6045671701431274,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.7252,
+      "step": 54
+    },
+    {
+      "epoch": 0.009283135636926251,
+      "eval_loss": 1.8240158557891846,
+      "eval_runtime": 851.6916,
+      "eval_samples_per_second": 5.752,
+      "eval_steps_per_second": 0.72,
+      "step": 54
+    },
+    {
+      "epoch": 0.009455045556128588,
+      "grad_norm": 2.49774169921875,
+      "learning_rate": 5e-05,
+      "loss": 3.7624,
+      "step": 55
+    },
+    {
+      "epoch": 0.009626955475330927,
+      "grad_norm": 1.8670446872711182,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.7836,
+      "step": 56
+    },
+    {
+      "epoch": 0.009798865394533264,
+      "grad_norm": 2.201873540878296,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 3.905,
+      "step": 57
+    },
+    {
+      "epoch": 0.009970775313735603,
+      "grad_norm": 1.9199110269546509,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.5981,
+      "step": 58
+    },
+    {
+      "epoch": 0.01014268523293794,
+      "grad_norm": 1.874394178390503,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 3.4784,
+      "step": 59
+    },
+    {
+      "epoch": 0.010314595152140279,
+      "grad_norm": 2.3110861778259277,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.7184,
+      "step": 60
+    },
+    {
+      "epoch": 0.010486505071342616,
+      "grad_norm": 1.9761158227920532,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 3.3884,
+      "step": 61
+    },
+    {
+      "epoch": 0.010658414990544955,
+      "grad_norm": 2.1625213623046875,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 3.8113,
+      "step": 62
+    },
+    {
+      "epoch": 0.010830324909747292,
+      "grad_norm": 2.4746720790863037,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 3.5716,
+      "step": 63
+    },
+    {
+      "epoch": 0.010830324909747292,
+      "eval_loss": 1.7517123222351074,
+      "eval_runtime": 851.0368,
+      "eval_samples_per_second": 5.757,
+      "eval_steps_per_second": 0.72,
+      "step": 63
+    },
+    {
+      "epoch": 0.01100223482894963,
+      "grad_norm": 2.145827531814575,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.7176,
+      "step": 64
+    },
+    {
+      "epoch": 0.011174144748151968,
+      "grad_norm": 1.8053840398788452,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 3.2714,
+      "step": 65
+    },
+    {
+      "epoch": 0.011346054667354307,
+      "grad_norm": 2.3119609355926514,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.2858,
+      "step": 66
+    },
+    {
+      "epoch": 0.011517964586556644,
+      "grad_norm": 2.341196060180664,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 3.5312,
+      "step": 67
+    },
+    {
+      "epoch": 0.011689874505758983,
+      "grad_norm": 2.4078032970428467,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 3.1824,
+      "step": 68
+    },
+    {
+      "epoch": 0.01186178442496132,
+      "grad_norm": 2.1059768199920654,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 3.412,
+      "step": 69
+    },
+    {
+      "epoch": 0.012033694344163659,
+      "grad_norm": 2.1562345027923584,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.4686,
+      "step": 70
+    },
+    {
+      "epoch": 0.012205604263365996,
+      "grad_norm": 2.128049612045288,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 3.568,
+      "step": 71
+    },
+    {
+      "epoch": 0.012377514182568335,
+      "grad_norm": 2.099907398223877,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.7875,
+      "step": 72
+    },
+    {
+      "epoch": 0.012377514182568335,
+      "eval_loss": 1.6961476802825928,
+      "eval_runtime": 851.7135,
+      "eval_samples_per_second": 5.752,
+      "eval_steps_per_second": 0.72,
+      "step": 72
+    },
+    {
+      "epoch": 0.012549424101770672,
+      "grad_norm": 2.117396593093872,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.0544,
+      "step": 73
+    },
+    {
+      "epoch": 0.01272133402097301,
+      "grad_norm": 2.188185691833496,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.3841,
+      "step": 74
+    },
+    {
+      "epoch": 0.012893243940175348,
+      "grad_norm": 2.4941723346710205,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 3.4467,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.3478299623424e+16,
+  "total_flos": 9.5217449435136e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null