Training in progress, step 10, checkpoint

checkpoint-10/adapter_config.json

@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "o_proj",
     "k_proj",
-    "q_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

checkpoint-10/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec2ae84c83281c2be94195f6460ed91b8dc598ab2bc5a97a9d7a410b064ede57
+oid sha256:d46729a49bc65312125c027d4dfd17938a0e34784daa55c4274e81b99761d8eb
 size 27297032

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c625e2f8ffef89aab694b1276bbf6dd0892425f211ad0a759c9926c15065fb
+oid sha256:e407504c0274504ea8ae1da85d4ff8aa72e90e9e5f40bbcacd01385ae49f44fc
 size 54678010

checkpoint-10/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ca330165ba8d7437a8214e8d593473913e426042eb1309ff957f321c801eaf
+oid sha256:1f446d1d665fe499a7e8afff583956eaaf2eb2926c47d7d56c7673b47ebeae0f
 size 14512

checkpoint-10/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8349807745c80d91093c27c78b812eff8d79a14aaa3ebc250fab32e1eba091f2
+oid sha256:23aa51841e50368d5625a032a866966dc4cb2985a862cc82a8208ccc23da1821
 size 14512

checkpoint-10/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.2503728866577148,
+  "best_metric": 1.2690961360931396,
   "best_model_checkpoint": "./mistral/29-02-24-Weni-test-folder-upload_Zeroshot-2_max_steps-30_batch_8_2024-02-29_ppid_7/checkpoint-10",
   "epoch": 0.006199628022318661,
   "eval_steps": 10,
@@ -10,10 +10,10 @@
   "log_history": [
     {
       "epoch": 0.01,
-      "eval_loss": 1.2503728866577148,
-      "eval_runtime": 207.1384,
-      "eval_samples_per_second": 13.841,
-      "eval_steps_per_second": 3.461,
+      "eval_loss": 1.2690961360931396,
+      "eval_runtime": 206.4706,
+      "eval_samples_per_second": 13.886,
+      "eval_steps_per_second": 3.473,
       "step": 10
     }
   ],
@@ -22,7 +22,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 5259188527693824.0,
+  "total_flos": 5359972082778112.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-10/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00a49a41db2912f3869dfbf7750585d354fbdd598aed12c4aa8d7c648e1e617b
+oid sha256:c8fa4a6d3049983810523685fa90b9ab4fc3fd64b76b897e665e803a3e9ada3b
 size 5112