Training in progress, epoch 0, checkpoint

last-checkpoint/config.json

@@ -56,7 +56,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 32128
 }

last-checkpoint/generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.34.1"
 }

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edbf65f6f6b2d902ca192fe35b3efd93add0d803274b4def7bd26dee546982fe
-size 1980860410
+oid sha256:bc5f7966ab751e227a273a7acdbf9909b12ac56502470ca806ef6c19af692daa
+size 1832

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9519ad1f203ec112bc005ea3f5aacffca3d057ed940f03bc40440539df41b908
+oid sha256:edda3e180dc7f3b528ecce2ee7125d509e7bce9dda2b822c296040dda25123dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4166a33b5520e0dfb0734abb46fce8eedf9514c1a2270d14609538201a3fae48
+oid sha256:b1860c7c6ca1e473d03a7cae1a98bbfbcae9f1a1ba246b538abe04ba78364f93
 size 1064

last-checkpoint/trainer_state.json

@@ -1,198 +1,38 @@
 {
-  "best_metric": 1.4382692575454712,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-7375",
-  "epoch": 5.0,
+  "best_metric": NaN,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-144",
+  "epoch": 0.9956784788245462,
   "eval_steps": 500,
-  "global_step": 7375,
+  "global_step": 144,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.34,
-      "learning_rate": 4.6610169491525425e-05,
-      "loss": 1.8922,
-      "step": 500
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 4.3220338983050854e-05,
-      "loss": 1.7522,
-      "step": 1000
-    },
     {
       "epoch": 1.0,
       "eval_bleu": 1.0,
       "eval_brevity_penalty": 1.0,
       "eval_length_ratio": 1.0,
-      "eval_loss": 1.4803038835525513,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 35996,
-      "eval_runtime": 295.5668,
-      "eval_samples_per_second": 6.652,
-      "eval_steps_per_second": 0.555,
-      "eval_translation_length": 35996,
-      "step": 1475
-    },
-    {
-      "epoch": 1.02,
-      "learning_rate": 3.983050847457627e-05,
-      "loss": 1.7275,
-      "step": 1500
-    },
-    {
-      "epoch": 1.36,
-      "learning_rate": 3.644067796610169e-05,
-      "loss": 1.6924,
-      "step": 2000
-    },
-    {
-      "epoch": 1.69,
-      "learning_rate": 3.305084745762712e-05,
-      "loss": 1.6815,
-      "step": 2500
-    },
-    {
-      "epoch": 2.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.4565129280090332,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 35935,
-      "eval_runtime": 291.4973,
-      "eval_samples_per_second": 6.744,
-      "eval_steps_per_second": 0.563,
-      "eval_translation_length": 35935,
-      "step": 2950
-    },
-    {
-      "epoch": 2.03,
-      "learning_rate": 2.9661016949152544e-05,
-      "loss": 1.6543,
-      "step": 3000
-    },
-    {
-      "epoch": 2.37,
-      "learning_rate": 2.627118644067797e-05,
-      "loss": 1.6515,
-      "step": 3500
-    },
-    {
-      "epoch": 2.71,
-      "learning_rate": 2.2881355932203392e-05,
-      "loss": 1.6408,
-      "step": 4000
-    },
-    {
-      "epoch": 3.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.446006178855896,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 36005,
-      "eval_runtime": 291.2917,
-      "eval_samples_per_second": 6.749,
-      "eval_steps_per_second": 0.563,
-      "eval_translation_length": 36005,
-      "step": 4425
-    },
-    {
-      "epoch": 3.05,
-      "learning_rate": 1.9491525423728814e-05,
-      "loss": 1.6183,
-      "step": 4500
-    },
-    {
-      "epoch": 3.39,
-      "learning_rate": 1.6101694915254237e-05,
-      "loss": 1.6291,
-      "step": 5000
-    },
-    {
-      "epoch": 3.73,
-      "learning_rate": 1.2711864406779661e-05,
-      "loss": 1.6058,
-      "step": 5500
-    },
-    {
-      "epoch": 4.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.4407896995544434,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 36007,
-      "eval_runtime": 291.6745,
-      "eval_samples_per_second": 6.74,
-      "eval_steps_per_second": 0.562,
-      "eval_translation_length": 36007,
-      "step": 5900
-    },
-    {
-      "epoch": 4.07,
-      "learning_rate": 9.322033898305085e-06,
-      "loss": 1.6139,
-      "step": 6000
-    },
-    {
-      "epoch": 4.41,
-      "learning_rate": 5.932203389830509e-06,
-      "loss": 1.5939,
-      "step": 6500
-    },
-    {
-      "epoch": 4.75,
-      "learning_rate": 2.5423728813559323e-06,
-      "loss": 1.5956,
-      "step": 7000
-    },
-    {
-      "epoch": 5.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.4382692575454712,
+      "eval_loss": NaN,
       "eval_precisions": [
         1.0,
         1.0,
         1.0,
         1.0
       ],
-      "eval_reference_length": 36000,
-      "eval_runtime": 292.0466,
-      "eval_samples_per_second": 6.732,
-      "eval_steps_per_second": 0.562,
-      "eval_translation_length": 36000,
-      "step": 7375
+      "eval_reference_length": 18771,
+      "eval_runtime": 122.4923,
+      "eval_samples_per_second": 8.392,
+      "eval_steps_per_second": 1.053,
+      "eval_translation_length": 18771,
+      "step": 144
     }
   ],
   "logging_steps": 500,
-  "max_steps": 7375,
-  "num_train_epochs": 5,
+  "max_steps": 2880,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 6.058048297107456e+16,
+  "total_flos": 6335375024848896.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb8f93fe1bfa9a74eac46b5edcc31c9e6cad75affbcfaa221d6576a2517e1b3e
+oid sha256:e101b52461267c553f7820ea490d90f0c52a8eee984bb696ad906e06ac49bd9a
 size 4664