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:df3298fa1c675faabc7ec43a93f90235da674b966a396ef310c766608f855222
+oid sha256:1d9ad5d64a03166c9bc524ad8d174996cf90d43192abaf327c997d4242ed6b6a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd062c740c47ad45cde936bd56841042a544bb919708e8339c9510c695fce67
+oid sha256:9ae808ff75202262c58fb5518155b1610a757f83dcb74ffa7177051c3a66bf76
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff117b2b37bde812847adc6eed8bdc759c3c07f5d1cbee1f5506533e03306f92
+oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
 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": 0.0011231033592021473,
+  "epoch": 0.001684655038803221,
   "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": 3.194,
       "step": 50
+    },
+    {
+      "epoch": 0.0011455654263861903,
+      "grad_norm": 1.9549919366836548,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 3.9626,
+      "step": 51
+    },
+    {
+      "epoch": 0.0011680274935702332,
+      "grad_norm": 1.655892252922058,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 3.8807,
+      "step": 52
+    },
+    {
+      "epoch": 0.0011904895607542762,
+      "grad_norm": 1.8876769542694092,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 3.6625,
+      "step": 53
+    },
+    {
+      "epoch": 0.0012129516279383193,
+      "grad_norm": 1.4899976253509521,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.6721,
+      "step": 54
+    },
+    {
+      "epoch": 0.0012129516279383193,
+      "eval_loss": 1.7459241151809692,
+      "eval_runtime": 3680.3071,
+      "eval_samples_per_second": 10.187,
+      "eval_steps_per_second": 1.274,
+      "step": 54
+    },
+    {
+      "epoch": 0.001235413695122362,
+      "grad_norm": 2.0449488162994385,
+      "learning_rate": 5e-05,
+      "loss": 3.4899,
+      "step": 55
+    },
+    {
+      "epoch": 0.0012578757623064052,
+      "grad_norm": 2.274089813232422,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.551,
+      "step": 56
+    },
+    {
+      "epoch": 0.001280337829490448,
+      "grad_norm": 2.418734550476074,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.9936,
+      "step": 57
+    },
+    {
+      "epoch": 0.001302799896674491,
+      "grad_norm": 1.5241280794143677,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 4.1763,
+      "step": 58
+    },
+    {
+      "epoch": 0.0013252619638585339,
+      "grad_norm": 1.6124359369277954,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 3.8093,
+      "step": 59
+    },
+    {
+      "epoch": 0.001347724031042577,
+      "grad_norm": 1.7779384851455688,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.73,
+      "step": 60
+    },
+    {
+      "epoch": 0.0013701860982266198,
+      "grad_norm": 1.860193133354187,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 3.7427,
+      "step": 61
+    },
+    {
+      "epoch": 0.0013926481654106628,
+      "grad_norm": 1.6981223821640015,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.6855,
+      "step": 62
+    },
+    {
+      "epoch": 0.0014151102325947057,
+      "grad_norm": 1.6831542253494263,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 3.7359,
+      "step": 63
+    },
+    {
+      "epoch": 0.0014151102325947057,
+      "eval_loss": 1.7401080131530762,
+      "eval_runtime": 3683.6574,
+      "eval_samples_per_second": 10.177,
+      "eval_steps_per_second": 1.272,
+      "step": 63
+    },
+    {
+      "epoch": 0.0014375722997787487,
+      "grad_norm": 1.6022491455078125,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.0342,
+      "step": 64
+    },
+    {
+      "epoch": 0.0014600343669627916,
+      "grad_norm": 1.8418630361557007,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 3.6607,
+      "step": 65
+    },
+    {
+      "epoch": 0.0014824964341468346,
+      "grad_norm": 1.5198544263839722,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.8486,
+      "step": 66
+    },
+    {
+      "epoch": 0.0015049585013308775,
+      "grad_norm": 1.892826795578003,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 3.1487,
+      "step": 67
+    },
+    {
+      "epoch": 0.0015274205685149205,
+      "grad_norm": 1.6396154165267944,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 3.4122,
+      "step": 68
+    },
+    {
+      "epoch": 0.0015498826356989633,
+      "grad_norm": 1.505338191986084,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 3.1957,
+      "step": 69
+    },
+    {
+      "epoch": 0.0015723447028830064,
+      "grad_norm": 1.8308162689208984,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.4024,
+      "step": 70
+    },
+    {
+      "epoch": 0.0015948067700670492,
+      "grad_norm": 1.852408766746521,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 3.4826,
+      "step": 71
+    },
+    {
+      "epoch": 0.0016172688372510923,
+      "grad_norm": 1.7535667419433594,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.8102,
+      "step": 72
+    },
+    {
+      "epoch": 0.0016172688372510923,
+      "eval_loss": 1.7378809452056885,
+      "eval_runtime": 3683.9491,
+      "eval_samples_per_second": 10.177,
+      "eval_steps_per_second": 1.272,
+      "step": 72
+    },
+    {
+      "epoch": 0.0016397309044351351,
+      "grad_norm": 1.760179877281189,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.7427,
+      "step": 73
+    },
+    {
+      "epoch": 0.0016621929716191782,
+      "grad_norm": 1.4445101022720337,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.7283,
+      "step": 74
+    },
+    {
+      "epoch": 0.001684655038803221,
+      "grad_norm": 1.5233592987060547,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 3.3569,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.26729100951552e+16,
+  "total_flos": 4.90093651427328e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null